© 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. 46056
    Prev
    Next
    INDEX
    Explanations

    letters and words that are capitalized in a non-standard pattern

    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
    400
    +0.07
    0.5%
    312
    +0.06
    0.5%
    446
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.07
    0.10
    373
    +0.06
    -0.20
    314
    +0.06
    -0.07
    Negative Logits
     CTR
    -0.46
    Constructed
    -0.43
    Pir
    -0.43
    bard
    -0.41
     organised
    -0.40
    jri
    -0.40
     Organ
    -0.39
    kamp
    -0.39
    byn
    -0.39
    holiday
    -0.38
    POSITIVE LOGITS
    CLASSIFIED
    0.53
    .,
    0.53
    .;
    0.49
    .?
    0.48
    âĶĢâĶĢâĶĢâĶĢ
    0.46
    orn
    0.46
    nee
    0.45
    mosp
    0.44
    Ͻ
    0.44
    ertain
    0.43
    Activations Density 10.524%

    No Known Activations