© 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. 1-RES-JB
    11. 23528
    Prev
    Next
    INDEX
    Explanations

    phrases related to something being an essential or necessary part of a whole

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to essential components or inseparability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.75
    ander
    -0.72
    \\\\\\\\
    -0.71
    haw
    -0.67
     Pants
    -0.67
    ilk
    -0.67
    aco
    -0.63
    cker
    -0.63
    elling
    -0.63
     Mostly
    -0.61
    POSITIVE LOGITS
     integral
    1.03
     adjunct
    0.76
    lesi
    0.74
    eatures
    0.73
    iour
    0.71
     accompan
    0.70
    ftime
    0.69
    quished
    0.68
    edded
    0.68
     facets
    0.67
    Activations Density 0.005%

    No Known Activations