© 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. 39668
    Prev
    Next
    INDEX
    Explanations

    names of locations with high activations on specific ones like "Britannia" and "Tacoma"

    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
    549
    +0.08
    0.6%
    679
    +0.08
    0.6%
    172
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.23
    326
    +0.08
    0.20
    195
    +0.08
    -0.01
    Negative Logits
    theless
    -0.49
    baugh
    -0.44
    PIN
    -0.44
     spiral
    -0.44
    arding
    -0.43
     deduction
    -0.42
    ball
    -0.41
    walking
    -0.41
    FORE
    -0.41
    nuts
    -0.40
    POSITIVE LOGITS
    emies
    0.76
    emia
    0.74
    alon
    0.61
    essor
    0.59
    illary
    0.58
    icians
    0.55
    uria
    0.55
    emi
    0.54
    ĩ
    0.53
    anches
    0.53
    Activations Density 6.867%

    No Known Activations