© 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. 3634
    Prev
    Next
    INDEX
    Explanations

    keywords related to dates, specific numbers, and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to events or conditions

    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
     thereof
    -0.60
    $.
    -0.56
     thereto
    -0.55
     outwe
    -0.49
    mpire
    -0.49
     ."
    -0.49
     theirs
    -0.49
    ]."
    -0.48
     respectively
    -0.46
    Balance
    -0.46
    POSITIVE LOGITS
    ccording
    0.59
     FANTASY
    0.58
    resa
    0.56
     GOODMAN
    0.55
     meanwhile
    0.54
     Background
    0.52
    odore
    0.52
     largeDownload
    0.51
     nutshell
    0.49
    ibliography
    0.46
    Activations Density 3.477%

    No Known Activations