© 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. 230
    Prev
    Next
    INDEX
    Explanations

    references to someone or something's status or reputation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "standing" in various contexts

    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
    ilers
    -0.86
    ffic
    -0.75
    egu
    -0.73
    xual
    -0.72
    quer
    -0.72
    esters
    -0.71
    xy
    -0.71
    ilic
    -0.71
    iler
    -0.70
    hammad
    -0.69
    POSITIVE LOGITS
    still
    1.02
     upright
    0.86
     tall
    0.76
     desks
    0.74
    lain
    0.68
    ARK
    0.66
     standing
    0.65
     downstairs
    0.65
     ov
    0.65
     steadfast
    0.64
    Activations Density 0.016%

    No Known Activations