© 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. 4014
    Prev
    Next
    INDEX
    Explanations

    information related to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant events or developments in a given field

    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
     goddamn
    -0.97
     godd
    -0.96
     damn
    -0.83
     darn
    -0.82
     Dude
    -0.81
     dude
    -0.80
     asshole
    -0.78
     fucking
    -0.78
     ______
    -0.76
     dudes
    -0.75
    POSITIVE LOGITS
     OECD
    0.96
     licences
    0.87
    hra
    0.84
     programme
    0.84
     organisations
    0.80
     analysed
    0.80
     envis
    0.80
     organis
    0.79
     programmes
    0.78
     Tata
    0.78
    Activations Density 1.362%

    No Known Activations