© 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. 9898
    Prev
    Next
    INDEX
    Explanations

    references to response, particularly in a more responsible or active context

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "respond" and its derivatives

    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
    BALL
    -0.73
     ANG
    -0.71
    fare
    -0.68
     Voy
    -0.68
    lay
    -0.66
     Alger
    -0.64
     Fritz
    -0.63
     Merlin
    -0.63
     Bav
    -0.62
     Lama
    -0.61
    POSITIVE LOGITS
    onding
    1.51
    ibilities
    1.40
    ible
    1.25
    onds
    1.16
    ond
    1.10
    awn
    1.09
    ibly
    1.07
    ibility
    1.05
    ublic
    1.05
    onder
    0.98
    Activations Density 0.031%

    No Known Activations