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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 6255
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest or indicate something

    oai_token-act-pair · gpt-3.5-turbo

    words that imply conclusion or inference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighth
    -0.73
    enium
    -0.73
    ciating
    -0.71
    pton
    -0.70
    pee
    -0.69
    ograp
    -0.69
    pez
    -0.67
    otype
    -0.67
    isec
    -0.65
    Synopsis
    -0.65
    POSITIVE LOGITS
     otherwise
    1.19
     that
    1.05
     causation
    0.84
     displeasure
    0.83
     collusion
    0.81
     imminent
    0.78
     they
    0.77
     widespread
    0.75
     impending
    0.75
     complicity
    0.74
    Activations Density 0.121%

    No Known Activations