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

    Neuronpedia

    Jacobian LensNEW
    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. 33371
    Prev
    Next
    INDEX
    Explanations

    locations or names containing the word "Cam" or "Camilla"

    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
    447
    +0.15
    0.7%
    326
    +0.12
    0.5%
    527
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.13
    527
    +0.12
    0.03
    484
    +0.11
    0.06
    Negative Logits
    ãģį
    -0.76
     enriched
    -0.73
     nomine
    -0.73
    lift
    -0.69
    Magikarp
    -0.68
    hips
    -0.66
     margins
    -0.65
     disadvant
    -0.64
     inference
    -0.62
    xual
    -0.61
    POSITIVE LOGITS
    oufl
    1.36
    illus
    1.00
    aign
    0.94
    illa
    0.93
    ERA
    0.89
    elia
    0.89
    illas
    0.86
     Newton
    0.86
    ming
    0.84
    illon
    0.83
    Activations Density 4.351%

    No Known Activations