© 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. 10-RES-JB
    11. 2702
    Prev
    Next
    INDEX
    Explanations

    actions or tasks that lead to a specific outcome

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions indicating purpose or intent in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.62
    eni
    -0.60
    wire
    -0.59
    degree
    -0.59
    egal
    -0.58
    ropolitan
    -0.57
    REL
    -0.56
    wick
    -0.55
    ascus
    -0.55
    ãģ£
    -0.55
    POSITIVE LOGITS
    othe
    1.08
    othes
    1.02
    apy
    0.94
     they
    0.93
    oner
    0.89
     that
    0.86
    bered
    0.82
     we
    0.81
    aps
    0.80
     nobody
    0.80
    Activations Density 0.070%

    No Known Activations