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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15636
    Prev
    Next
    INDEX
    Explanations

    mentions where something is of small quantity or significance

    oai_token-act-pair · gpt-3.5-turbo

    instances where "little" is mentioned in relation to various topics

    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
    ser
    -0.74
    llers
    -0.71
    kus
    -0.69
    dor
    -0.69
    agents
    -0.68
    ses
    -0.68
    atche
    -0.64
    midt
    -0.64
    ħĭ
    -0.63
    wered
    -0.63
    POSITIVE LOGITS
     else
    0.99
     consolation
    0.86
     resemblance
    0.85
     doubt
    0.83
     patience
    0.83
     sympathy
    0.81
     indication
    0.81
     recourse
    0.79
     inclination
    0.77
     fuss
    0.77
    Activations Density 0.037%

    No Known Activations