© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6477
    Prev
    Next
    INDEX
    Explanations

    proper names and initials of individuals and organizations

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to advertisements or promotional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.80
    fork
    -0.69
    İĭ
    -0.68
     Sv
    -0.66
    rences
    -0.66
    ersed
    -0.62
    venants
    -0.61
    lyak
    -0.61
    prus
    -0.61
     Byz
    -0.60
    POSITIVE LOGITS
    ushi
    0.82
    tu
    0.81
    uku
    0.74
    abi
    0.69
    asta
    0.69
    anamo
    0.67
    aba
    0.65
    anga
    0.65
    ucc
    0.64
    oglu
    0.63
    Activations Density 0.137%

    No Known Activations