© 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. 6437
    Prev
    Next
    INDEX
    Explanations

    questions directed at the reader

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "you" in various contexts

    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
    ruciating
    -0.79
    accompan
    -0.75
    ospital
    -0.73
    umber
    -0.70
    inelli
    -0.69
    apo
    -0.69
    ges
    -0.66
    Lago
    -0.66
    arc
    -0.65
    "},
    -0.64
    POSITIVE LOGITS
     guys
    1.11
     ever
    1.03
    ?'
    0.92
     subscribed
    0.89
     intend
    0.89
    tub
    0.87
    ?'"
    0.87
     prefer
    0.87
    ?"
    0.86
     wanna
    0.85
    Activations Density 0.041%

    No Known Activations