© 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. 14982
    Prev
    Next
    INDEX
    Explanations

    mentions of "cher" with different prefixes such as "pit", "ben", "sky" or "wat"

    oai_token-act-pair · gpt-3.5-turbo

    the term "watchers" or its variations throughout the text

    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
    ital
    -0.68
     balance
    -0.62
    case
    -0.61
    sp
    -0.61
    Rich
    -0.60
     conditional
    -0.60
    Minor
    -0.60
    rip
    -0.59
    itor
    -0.57
    val
    -0.57
    POSITIVE LOGITS
    poons
    1.32
    chers
    1.29
    hooting
    1.18
    mith
    1.12
    poon
    1.11
    pread
    0.98
    terday
    0.97
    uggest
    0.97
    aurus
    0.97
    ervatives
    0.93
    Activations Density 0.024%

    No Known Activations