© 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. 1-RES-JB
    11. 20183
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to immediate actions or responses

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "instantly" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ANGEL
    -0.77
     Millennium
    -0.75
    pel
    -0.70
     Hann
    -0.70
    pects
    -0.66
    may
    -0.66
    ger
    -0.64
    llor
    -0.63
     Nost
    -0.62
     Bureau
    -0.62
    POSITIVE LOGITS
    aneously
    1.48
     Leilan
    1.12
     instantly
    0.97
     thereafter
    0.83
    aneous
    0.83
    idious
    0.81
     recognizable
    0.79
     recogn
    0.78
     identifiable
    0.78
    ingu
    0.77
    Activations Density 0.007%

    No Known Activations