© 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. 9053
    Prev
    Next
    INDEX
    Explanations

    keywords related to technical or specialized terms, often presented in the context of reports or documents

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Int" and its variations, likely related to internet or intelligence 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
     Gleaming
    -0.83
    代
    -0.80
    wordpress
    -0.79
    76561
    -0.77
    artifacts
    -0.77
    mith
    -0.76
    ILA
    -0.76
    lling
    -0.74
    interstitial
    -0.68
    éĹĺ
    -0.67
    POSITIVE LOGITS
    elligence
    1.29
    ensity
    1.27
    ellect
    1.27
    estinal
    1.09
    ention
    1.07
    ENTION
    1.04
    uitive
    0.97
    ellig
    0.96
    ensive
    0.92
    elligent
    0.92
    Activations Density 0.009%

    No Known Activations