Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 1714
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    genic
    -0.68
    ournals
    -0.64
    ollah
    -0.62
    markets
    -0.61
    auc
    -0.60
    ulz
    -0.59
    rossover
    -0.59
     Airl
    -0.58
    fam
    -0.58
    bek
    -0.58
    POSITIVE LOGITS
    atis
    0.86
     Wage
    0.72
    MENT
    0.68
    CLASS
    0.68
    mental
    0.67
    tale
    0.66
    tons
    0.66
    SpaceEngineers
    0.66
    sbm
    0.64
    ton
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.