© 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. 8-RES-JB
    11. 18534
    Prev
    Next
    INDEX
    Explanations

    email-related actions

    oai_token-act-pair · gpt-3.5-turbo

    links and calls to action related to sharing or emailing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    going
    -0.70
    beit
    -0.67
    ensical
    -0.63
    mand
    -0.63
    zl
    -0.63
     Pilgrim
    -0.62
    puter
    -0.61
     headaches
    -0.60
    keeper
    -0.59
     pige
    -0.58
    POSITIVE LOGITS
     enlarge
    1.11
    ĵĺ
    0.77
     zoom
    0.76
     enlarg
    0.73
     thumbnail
    0.73
     Submit
    0.71
     shrink
    0.70
    hide
    0.67
    MSN
    0.67
     attach
    0.67
    Activations Density 0.034%

    No Known Activations