© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6415
    Prev
    Next
    INDEX
    Explanations

    photo credits with names prominently featured in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to photography credits and attributions in media

    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
    ãĢIJ
    -0.64
     :=
    -0.61
    answered
    -0.60
    yre
    -0.58
    within
    -0.57
     footsteps
    -0.56
    rower
    -0.56
     behold
    -0.54
    ãĢİ
    -0.53
     rang
    -0.52
    POSITIVE LOGITS
    .)
    1.13
     .)
    1.13
    )]
    1.10
    â̦)
    1.10
    )"
    1.07
    )
    1.06
    ):
    1.02
    .):
    0.99
    .),
    0.97
    >)
    0.96
    Activations Density 0.101%

    No Known Activations