© 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 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. 8-RES-JB
    11. 3872
    Prev
    Next
    INDEX
    Explanations

    words related to defects or issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to defects or deficiencies

    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
    fare
    -0.78
    76561
    -0.73
    iland
    -0.73
    eter
    -0.67
    apest
    -0.66
    stead
    -0.66
    ahon
    -0.64
    ffield
    -0.64
    elcome
    -0.63
    dress
    -0.63
    POSITIVE LOGITS
    ions
    0.89
    icient
    0.85
    ively
    0.80
    inia
    0.77
    rees
    0.77
    acies
    0.76
    ioned
    0.74
    ion
    0.72
    orius
    0.72
    escent
    0.71
    Activations Density 0.067%

    No Known Activations