© 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. 9-RES-JB
    11. 9106
    Prev
    Next
    INDEX
    Explanations

    phrases related to important or impactful actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant actions, issues, or concepts in a socio-political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uly
    -0.75
     Carbuncle
    -0.75
    rily
    -0.71
    appropriately
    -0.70
    particularly
    -0.69
    ately
    -0.68
    aciously
    -0.67
    cellaneous
    -0.65
    especially
    -0.65
    successfully
    -0.64
    POSITIVE LOGITS
    wives
    0.79
    ITNESS
    0.72
    ument
    0.71
    ifier
    0.70
    UID
    0.66
    behind
    0.65
    govtrack
    0.65
    éĹ
    0.64
    ür
    0.62
    Ò
    0.62
    Activations Density 0.377%

    No Known Activations