© 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. 0-RES-JB
    11. 6881
    Prev
    Next
    INDEX
    Explanations

    terms related to fundamental questions and doubts

    oai_token-act-pair · gpt-3.5-turbo

    concepts or terms related to foundational issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Germ
    -0.68
    condition
    -0.66
     Levin
    -0.65
    uncture
    -0.63
     msec
    -0.63
    ratom
    -0.62
    dayName
    -0.62
    lement
    -0.62
     primates
    -0.61
     Lever
    -0.60
    POSITIVE LOGITS
    achus
    0.76
    ysc
    0.75
    akin
    0.74
    Adds
    0.73
    aki
    0.67
    usha
    0.66
    heads
    0.66
    Ú
    0.63
    icism
    0.63
    CRE
    0.62
    Activations Density 0.000%

    No Known Activations