© 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. 4-RES-JB
    11. 13060
    Prev
    Next
    INDEX
    Explanations

    instances where someone is trying to resolve a situation, often by seeking permission or assistance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to have."

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

    No Comments

    Negative Logits
     fireball
    -0.67
    catentry
    -0.66
     hostage
    -0.63
     anticipating
    -0.59
     wounding
    -0.59
     denouncing
    -0.59
    etter
    -0.57
    typ
    -0.56
     parachute
    -0.56
     outp
    -0.55
    POSITIVE LOGITS
     been
    1.07
     gotten
    1.00
    been
    0.93
     taken
    0.86
    ardless
    0.84
     Been
    0.83
     seen
    0.83
    gotten
    0.82
     done
    0.80
     undergone
    0.80
    Activations Density 0.165%

    No Known Activations