© 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. 2821
    Prev
    Next
    INDEX
    Explanations

    adjectives describing textures or sensations

    oai_token-act-pair · gpt-3.5-turbo

    references to touch-related concepts or themes

    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
    ichick
    -0.79
    KK
    -0.67
     Ruins
    -0.66
    orks
    -0.65
    etheus
    -0.65
    hement
    -0.62
     looph
    -0.61
    swers
    -0.61
    ategory
    -0.59
    steen
    -0.59
    POSITIVE LOGITS
    arget
    0.79
    onica
    0.76
     scrimmage
    0.74
     inappropriately
    0.69
    tle
    0.68
    abus
    0.67
     toes
    0.67
    meter
    0.67
     fingertips
    0.66
     nail
    0.64
    Activations Density 0.074%

    No Known Activations