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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 10025
    Prev
    Next
    INDEX
    Explanations

    references to clinical trials

    oai_token-act-pair · gpt-3.5-turbo

    mentions of clinical trials

    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
    flush
    -0.78
    BN
    -0.71
    Security
    -0.64
    Language
    -0.62
    leted
    -0.62
    CLOSE
    -0.61
    Solid
    -0.61
    si
    -0.61
    iak
    -0.60
    afort
    -0.60
    POSITIVE LOGITS
     trials
    1.44
     Trials
    1.41
     trial
    1.03
     Trial
    0.95
    avorite
    0.86
     testing
    0.80
    trial
    0.80
     hearings
    0.77
    neys
    0.77
    hower
    0.75
    Activations Density 0.008%

    No Known Activations