© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 40750
    Prev
    Next
    INDEX
    Explanations

    words related to discharging, such as "discharge," "discharged," "discharges," and related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.09
    0.8%
    447
    +0.09
    0.7%
    270
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.09
    0.17
    150
    +0.09
    0.07
    577
    +0.06
    0.10
    Negative Logits
    aque
    -0.45
    Ear
    -0.40
    aques
    -0.39
    apa
    -0.39
    ppa
    -0.38
    ellen
    -0.37
    Cru
    -0.37
     Beir
    -0.36
    sem
    -0.36
    ador
    -0.36
    POSITIVE LOGITS
     discharge
    0.63
    ysis
    0.55
    enture
    0.51
     discharged
    0.50
    owship
    0.49
    luent
    0.49
    ertation
    0.48
    uations
    0.48
    ploy
    0.42
    LECT
    0.42
    Activations Density 12.469%

    No Known Activations