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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21812
    Prev
    Next
    INDEX
    Explanations

    terms related to rapid and involuntary physical reactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to responsiveness and reflexivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Peninsula
    -0.74
    AST
    -0.68
    OTAL
    -0.68
    IRD
    -0.68
     thirds
    -0.66
     dear
    -0.65
    agine
    -0.61
    butt
    -0.60
     thence
    -0.59
    riage
    -0.59
    POSITIVE LOGITS
    es
    2.29
    ively
    1.32
    esian
    1.20
    ername
    1.16
    ed
    1.15
    ions
    1.14
    ecake
    1.14
    esville
    1.13
    iveness
    1.10
    engers
    1.04
    Activations Density 0.070%

    No Known Activations