© 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. 3270
    Prev
    Next
    INDEX
    Explanations

    mentions of proper nouns or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "AK" related to Alaska, frequently appearing 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
    weights
    -0.75
     Weasley
    -0.72
     istg
    -0.69
     guiIcon
    -0.67
    ãĤ£
    -0.67
    drops
    -0.66
    weight
    -0.65
     boosters
    -0.60
     guiActiveUn
    -0.60
    ãĤ¡
    -0.59
    POSITIVE LOGITS
    AK
    0.93
    arak
    0.89
    AY
    0.88
    NESS
    0.81
    ansas
    0.78
    PLIC
    0.78
    ay
    0.77
    umar
    0.77
    ernel
    0.77
    AIN
    0.76
    Activations Density 0.003%

    No Known Activations