© 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. 2-RES-JB
    11. 24052
    Prev
    Next
    INDEX
    Explanations

    references to additional or supplementary items, particularly in terms of cost or effort

    oai_token-act-pair · gpt-3.5-turbo

    references to additional resources or efforts beyond what is typical or expected

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.79
    76561
    -0.71
     Trend
    -0.70
     CrossRef
    -0.70
    \\\\\\\\
    -0.68
    geist
    -0.68
     Brist
    -0.67
    atche
    -0.67
    Trend
    -0.67
    HCR
    -0.66
    POSITIVE LOGITS
    ordinary
    1.18
    judicial
    1.03
    visor
    0.97
     extras
    0.96
    verted
    0.95
     virgin
    0.93
     extra
    0.86
     goodies
    0.85
     precaution
    0.78
    veh
    0.77
    Activations Density 0.009%

    No Known Activations