© 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. 6-RES-JB
    11. 19806
    Prev
    Next
    INDEX
    Explanations

    terms related to political entities or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "PTI"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flies
    -0.91
    hold
    -0.91
    bye
    -0.80
    cle
    -0.76
    weights
    -0.72
    bars
    -0.72
    mble
    -0.70
    perse
    -0.70
    ãĤ£
    -0.70
    nces
    -0.69
    POSITIVE LOGITS
    ypes
    0.95
    ION
    0.92
     Cruiser
    0.85
    EMBER
    0.84
    ember
    0.84
    OGR
    0.82
    itious
    0.80
    BN
    0.79
    WS
    0.78
    ARGET
    0.78
    Activations Density 0.023%

    No Known Activations