© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14113
    Prev
    Next
    INDEX
    Explanations

    words related to programming, codes, and technical terms such as 'Cache', 'Loader', 'Provider', 'System', 'Object', 'String', 'View', 'Role', 'Class'

    oai_token-act-pair · gpt-3.5-turbo

    elements related to user and cache management in programming

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    terday
    -1.03
    theless
    -0.83
    ecd
    -0.80
    ctica
    -0.77
    ischer
    -0.74
    lie
    -0.72
    sov
    -0.72
    anwhile
    -0.72
    teness
    -0.71
    prising
    -0.70
    POSITIVE LOGITS
    Input
    1.15
    Output
    1.12
    String
    1.11
    Field
    1.09
    Error
    1.09
    Definition
    1.08
    Component
    1.06
    Object
    1.06
    Ut
    1.06
    Interface
    1.05
    Activations Density 0.103%

    No Known Activations