© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13844
    Prev
    Next
    INDEX
    Explanations

    topics related to political parties and environmental issues

    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
    459
    +0.22
    0.9%
    269
    +0.16
    0.6%
    70
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.22
    0.08
    656
    +0.16
    0.07
    269
    +0.15
    0.04
    Negative Logits
    orically
    -1.00
    nces
    -0.90
    gerald
    -0.88
    Downloadha
    -0.87
    mble
    -0.86
    illery
    -0.82
    ebin
    -0.82
    oldemort
    -0.80
    illation
    -0.80
    ̶
    -0.79
    POSITIVE LOGITS
    grass
    1.37
    leaf
    1.21
    stuff
    1.16
    house
    1.08
    houses
    1.06
     Lantern
    1.05
    wich
    1.03
    haven
    1.03
    baum
    1.02
    lit
    1.01
    Activations Density 8.205%

    No Known Activations