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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4615
    Prev
    Next
    INDEX
    Explanations

    words related to electric discharges and related actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discharge or removal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chess
    -0.90
     Sche
    -0.82
     Hispan
    -0.78
    Kit
    -0.75
    Tokens
    -0.73
     chess
    -0.73
    oen
    -0.70
     Wonders
    -0.69
     Tat
    -0.69
    lems
    -0.68
    POSITIVE LOGITS
     discharge
    4.03
     discharged
    3.58
    charges
    1.55
    charge
    1.39
    charging
    1.35
    Charge
    1.15
     remission
    0.97
     recharge
    0.97
     termination
    0.97
     wounding
    0.93
    Activations Density 0.017%

    No Known Activations