Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19890
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data analysis and statistical analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic factors and conditions

    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
    DragonMagazine
    -0.58
    oso
    -0.55
     Emir
    -0.50
    âĢİ
    -0.47
    vier
    -0.46
    ById
    -0.45
    eny
    -0.45
     Ernst
    -0.44
    UGC
    -0.43
     Marina
    -0.42
    POSITIVE LOGITS
    +.
    0.68
    $.
    0.65
    >.
    0.63
    }.
    0.63
    .$
    0.61
    %.
    0.61
    _.
    0.61
    .'
    0.59
    .�
    0.58
    ().
    0.57
    Activations Density 1.629%

    No Known Activations