© 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. 9-RES-JB
    11. 16265
    Prev
    Next
    INDEX
    Explanations

    words related to criticisms or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "di-" related to various contexts or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    witz
    -0.75
     Rudd
    -0.71
    ï¸ı
    -0.70
     totality
    -0.69
    INGS
    -0.68
    leigh
    -0.67
    ORTS
    -0.66
    ãģĨ
    -0.64
     spare
    -0.64
     Heard
    -0.63
    POSITIVE LOGITS
    urnal
    1.42
    abol
    1.39
    ocese
    1.36
    abolic
    1.25
    agon
    1.15
    plom
    1.12
    ablo
    1.11
    agram
    1.08
    agonal
    1.02
    adem
    1.02
    Activations Density 0.018%

    No Known Activations