© 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. 11-RES-JB
    11. 10174
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions that involve influence, control, or response

    oai_token-act-pair · gpt-3.5-turbo

    words indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abiding
    -0.85
    afety
    -0.75
    answered
    -0.67
    76561
    -0.66
    ById
    -0.66
     apologised
    -0.66
    checking
    -0.64
     Died
    -0.63
    cens
    -0.63
    breeding
    -0.63
    POSITIVE LOGITS
     elevate
    0.91
     begin
    0.91
     accelerate
    0.91
     unleash
    0.89
     extend
    0.88
     bring
    0.85
     widen
    0.85
     seize
    0.83
     expand
    0.83
     plunge
    0.83
    Activations Density 0.490%

    No Known Activations