© 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. 16496
    Prev
    Next
    INDEX
    Explanations

    verbs following the pattern of 'r' followed by a number, possibly indicating intensity or degree of action

    oai_token-act-pair · gpt-3.5-turbo

    words related to criticism or complaints

    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
     GOODMAN
    -0.69
     ROM
    -0.67
     cardio
    -0.65
     daylight
    -0.65
     hers
    -0.63
     reversible
    -0.63
    RON
    -0.62
     mine
    -0.60
     ours
    -0.60
    ãĤ´
    -0.60
    POSITIVE LOGITS
    attle
    1.34
    ained
    1.32
    ammed
    1.31
    oused
    1.29
    ifling
    1.27
    umbled
    1.26
    ifled
    1.25
    ationally
    1.24
    ambling
    1.24
    ipples
    1.19
    Activations Density 0.015%

    No Known Activations