© 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. 7-RES-JB
    11. 8662
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical attributes or characteristics of individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe physical attributes or characteristics

    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
    icity
    -0.74
     persisted
    -0.72
    reon
    -0.72
    icals
    -0.72
    erity
    -0.68
    Iss
    -0.63
    Shape
    -0.63
     Eventually
    -0.62
     furthermore
    -0.61
    apter
    -0.61
    POSITIVE LOGITS
     typical
    0.82
     ordinary
    0.75
    ¥µ
    0.72
     conventional
    0.69
     wildfire
    0.68
     childbirth
    0.68
     seasoned
    0.67
     medieval
    0.66
    cham
    0.66
     gau
    0.65
    Activations Density 0.568%

    No Known Activations