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. 3-RES-JB
    6. 19065
    Prev
    Next
    INDEX
    Explanations

    terms related to biology and bodily functions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological and scientific concepts, particularly those concerning follicles and proteins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parish
    -0.81
    IELD
    -0.80
    BIP
    -0.80
     Inquisitor
    -0.74
     Hercules
    -0.74
     Grip
    -0.72
    ILLE
    -0.71
    VIS
    -0.70
     Daddy
    -0.70
     Vader
    -0.68
    POSITIVE LOGITS
    utive
    1.13
    ographed
    0.97
    icity
    0.96
    icative
    0.96
    etime
    0.96
    atory
    0.93
    atform
    0.92
    ative
    0.91
    ues
    0.87
    ularity
    0.86
    Activations Density 0.025%

    No Known Activations