© 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. 7-RES-JB
    11. 5232
    Prev
    Next
    INDEX
    Explanations

    initials or acronyms followed by a number, potentially related to trademarks or branding

    oai_token-act-pair · gpt-3.5-turbo

    trademarks or brand references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.95
    furt
    -0.84
    ships
    -0.83
    vous
    -0.76
    vier
    -0.74
    vernment
    -0.74
    shall
    -0.73
    fman
    -0.69
    rigan
    -0.68
    ger
    -0.68
    POSITIVE LOGITS
    asters
    0.91
    obile
    0.90
    astics
    0.82
    agic
    0.79
    NT
    0.79
    TI
    0.78
    otor
    0.76
    astic
    0.74
    RC
    0.72
    obiles
    0.72
    Activations Density 0.051%

    No Known Activations