© 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. 4-RES-JB
    11. 12600
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations and their activities

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

    No Comments

    Negative Logits
    IGH
    -0.74
    ĺħ
    -0.72
    inges
    -0.69
    inge
    -0.69
    ħĭ
    -0.62
    selves
    -0.61
    ĪĴ
    -0.60
    £ı
    -0.60
     arri
    -0.59
     hem
    -0.59
    POSITIVE LOGITS
    dor
    0.76
    cair
    0.75
    TION
    0.74
    teen
    0.73
    rans
    0.71
    pole
    0.70
    istics
    0.70
    cent
    0.69
    encies
    0.69
    lot
    0.69
    Activations Density 0.019%

    No Known Activations