© 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. 461
    Prev
    Next
    INDEX
    Explanations

    dates in the format of month-day-year

    oai_token-act-pair · gpt-3.5-turbo

    references to numeric values or scores related to performance or rankings

    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
     Dickinson
    -0.69
     Rounds
    -0.65
    ertodd
    -0.64
     Ezra
    -0.64
     Reborn
    -0.61
    DERR
    -0.60
     ðŁij
    -0.59
     Shank
    -0.59
     scramble
    -0.59
     practice
    -0.58
    POSITIVE LOGITS
    cell
    0.90
    sama
    0.90
    comments
    0.89
    esque
    0.85
    recomm
    0.84
    inf
    0.83
    cent
    0.83
    length
    0.83
    20439
    0.81
    prison
    0.80
    Activations Density 0.197%

    No Known Activations