© 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. 8-RES-JB
    11. 6256
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions of interest in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of interest in various topics or fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rome
    -0.67
    pex
    -0.65
    llan
    -0.64
    å°Ĩ
    -0.63
    xon
    -0.62
    prus
    -0.60
    ELF
    -0.59
    ut
    -0.57
    sung
    -0.56
     seams
    -0.56
    POSITIVE LOGITS
    enza
    0.82
     rate
    0.78
     Groups
    0.78
     trolling
    0.72
     rates
    0.72
     Rate
    0.71
    group
    0.70
    ocene
    0.70
     seekers
    0.70
    Rate
    0.69
    Activations Density 0.030%

    No Known Activations