Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45350
    Prev
    Next
    INDEX
    Explanations

    references to love and relationships

    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
    +0.23
    1.0%
    459
    +0.15
    0.6%
    161
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.23
    0.12
    128
    +0.15
    0.10
    513
    +0.14
    0.07
    Negative Logits
    ulhu
    -0.92
    TPPStreamerBot
    -0.89
    icter
    -0.88
    interstitial
    -0.86
    acco
    -0.85
    chnology
    -0.83
    vernment
    -0.82
    DERR
    -0.80
     helicop
    -0.78
    ħĭ
    -0.78
    POSITIVE LOGITS
    joy
    1.13
    birds
    1.12
    making
    1.04
     uncond
    0.98
    bird
    0.94
    fully
    0.94
    giving
    0.94
     affair
    0.89
    good
    0.87
    ably
    0.85
    Activations Density 9.166%

    No Known Activations