© 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. 7-RES-JB
    11. 6445
    Prev
    Next
    INDEX
    Explanations

    notable collaborations between individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of collaboration or association between subjects

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    othal
    -0.78
    lock
    -0.76
    physical
    -0.75
    hole
    -0.75
    holes
    -0.74
    prus
    -0.74
    ysis
    -0.70
    dain
    -0.70
    lus
    -0.70
    activity
    -0.70
    POSITIVE LOGITS
     overseen
    1.05
     headquartered
    1.03
     styled
    1.01
     distributed
    0.92
     affiliated
    0.91
     financed
    0.91
     supplemented
    0.91
     staffed
    0.91
     thence
    0.90
     presided
    0.89
    Activations Density 0.284%

    No Known Activations