© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7460
    Prev
    Next
    INDEX
    Explanations

    references to specific historical dates or events

    oai_token-act-pair · gpt-3.5-turbo

    lines or segments with distinctive formatting or patterns

    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
    prus
    -0.82
    pes
    -0.79
    ntil
    -0.76
    alty
    -0.74
    cled
    -0.73
    hare
    -0.72
    cious
    -0.72
    aurus
    -0.72
    pell
    -0.70
    xon
    -0.69
    POSITIVE LOGITS
     Liang
    0.70
    sen
    0.69
     è£ıè
    0.68
     Primordial
    0.66
    }}}
    0.64
    é¾įå
    0.63
    oven
    0.61
     Trog
    0.60
     Assembly
    0.60
     Peng
    0.60
    Activations Density 0.000%

    No Known Activations