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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21921
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to "cro" or related terms, indicating a focus on crop or agricultural themes

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

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.76
    ERSON
    -0.74
    UAL
    -0.74
    endez
    -0.74
    hips
    -0.72
    ullah
    -0.72
    VERTIS
    -0.71
     sidx
    -0.71
    imental
    -0.70
    IELD
    -0.67
    POSITIVE LOGITS
     cro
    0.99
    oks
    0.96
    pper
    0.92
    cro
    0.86
    grain
    0.86
    oked
    0.82
    pped
    0.78
    opa
    0.77
    pping
    0.77
    artisan
    0.77
    Activations Density 0.004%

    No Known Activations