© 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. 23385
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific militant groups and their leaders

    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
     crochet
    -0.68
    livious
    -0.68
     erection
    -0.66
    acebook
    -0.64
     xp
    -0.63
     Entered
    -0.61
     Pony
    -0.59
     Nadu
    -0.59
     +/-
    -0.59
     gears
    -0.59
    POSITIVE LOGITS
    azeera
    1.09
    awi
    0.99
    aghd
    0.96
    abi
    0.86
    adr
    0.84
    aq
    0.83
    aida
    0.82
    adi
    0.82
    andi
    0.81
    aeda
    0.81
    Activations Density 0.053%

    No Known Activations