© 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. 12504
    Prev
    Next
    INDEX
    Explanations

    dates and times presented in a specific format, likely related to scheduling events or programs

    oai_token-act-pair · gpt-3.5-turbo

    repeated punctuation marks, particularly commas

    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
    DERR
    -0.69
    sylv
    -0.68
     behavi
    -0.67
    natureconservancy
    -0.66
     detectors
    -0.64
    conom
    -0.64
    uggest
    -0.64
    STDOUT
    -0.64
    Sov
    -0.64
    interstitial
    -0.61
    POSITIVE LOGITS
     huh
    0.90
     etc
    0.83
    032
    0.81
     eh
    0.80
     LLC
    0.77
     please
    0.76
     supra
    0.75
     ?)
    0.74
    048
    0.74
     ISBN
    0.72
    Activations Density 0.610%

    No Known Activations