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. 34076
    Prev
    Next
    INDEX
    Explanations

    situations where a decision has to be made under constraint or necessity

    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%
    506
    +0.09
    0.5%
    393
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.15
    0.38
    640
    +0.09
    0.33
    283
    +0.08
    0.03
    Negative Logits
    cre
    -0.57
    comed
    -0.56
    worm
    -0.54
    ritical
    -0.53
    UG
    -0.52
    borough
    -0.52
    Registered
    -0.51
    STAT
    -0.50
    Sec
    -0.50
    urance
    -0.49
    POSITIVE LOGITS
     choices
    0.74
    Option
    0.73
     choosing
    0.71
     chose
    0.66
     choose
    0.65
     option
    0.65
     options
    0.65
     selecting
    0.64
     choice
    0.63
     expend
    0.63
    Activations Density 18.111%

    No Known Activations