© 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. 8-RES-JB
    11. 7578
    Prev
    Next
    INDEX
    Explanations

    words related to specific proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the presence of words or roots related to "Biv" or similar sounding terms, potentially indicating a focus on specific names or entities

    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
     FTC
    -0.63
     reven
    -0.59
     invention
    -0.55
     Vega
    -0.54
     glyph
    -0.53
    FORMATION
    -0.53
     todd
    -0.53
     Jed
    -0.52
     Acad
    -0.52
     Lann
    -0.51
    POSITIVE LOGITS
    lehem
    0.99
    pillar
    0.97
    levard
    0.96
    apest
    0.96
    wana
    0.90
    abase
    0.89
    aneers
    0.81
    ombo
    0.79
    rill
    0.78
    ause
    0.77
    Activations Density 0.136%

    No Known Activations