© 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. 7698
    Prev
    Next
    INDEX
    Explanations

    words related to processes or actions being performed

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to analysis, assessment, and evaluation

    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
    selves
    -0.81
    $.
    -0.71
    +.
    -0.64
    ecause
    -0.64
     [|
    -0.63
    Eva
    -0.63
    Ø©
    -0.59
    !.
    -0.58
    itored
    -0.58
     Oval
    -0.57
    POSITIVE LOGITS
     consists
    0.83
     comprises
    0.74
     consisted
    0.74
     is
    0.67
     begins
    0.65
     continues
    0.63
     contains
    0.62
     isn
    0.62
     has
    0.62
     revolves
    0.61
    Activations Density 0.608%

    No Known Activations