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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45169
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial investments and spending

    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
    0.9%
    193
    +0.09
    0.5%
    549
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.15
    0.06
    12
    +0.09
    0.06
    70
    +0.09
    0.09
    Negative Logits
     Gemini
    -0.59
     Blaz
    -0.59
    DragonMagazine
    -0.51
    runners
    -0.50
    ban
    -0.50
     Machina
    -0.49
    fen
    -0.48
    ĺħ
    -0.48
    âĶĢ
    -0.48
    Ĥİ
    -0.47
    POSITIVE LOGITS
    itures
    0.90
    iture
    0.89
    igate
    0.85
    iment
    0.67
    igating
    0.66
    ayers
    0.66
    ulously
    0.65
    ativity
    0.63
    atively
    0.63
    enza
    0.59
    Activations Density 7.693%

    No Known Activations