© 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. 3-RES-JB
    11. 11362
    Prev
    Next
    INDEX
    Explanations

    verbs related to successfully accomplishing a task or goal

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "managed" indicating successes or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icipated
    -0.96
    formance
    -0.81
    azi
    -0.71
    amd
    -0.70
    inner
    -0.69
    prev
    -0.68
    PU
    -0.68
    origin
    -0.67
    empty
    -0.67
    func
    -0.65
    POSITIVE LOGITS
     manage
    0.95
     manages
    0.93
     managed
    0.84
     Pradesh
    0.81
    ITIES
    0.71
    ices
    0.65
     hemor
    0.63
    arians
    0.62
    ges
    0.62
     manag
    0.61
    Activations Density 0.017%

    No Known Activations