© 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. 7-RES-JB
    11. 175
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles of people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities involved in examination or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENCY
    -0.66
     Dangerous
    -0.66
     onstage
    -0.62
     publicity
    -0.62
    href
    -0.61
     pseudonym
    -0.61
    apesh
    -0.60
    due
    -0.59
     Fairy
    -0.59
    apo
    -0.59
    POSITIVE LOGITS
    RESULTS
    0.98
     discern
    0.88
     comprehension
    0.83
    inguishable
    0.80
     attest
    0.77
     noticed
    0.76
     amazed
    0.75
     uncover
    0.75
    ousands
    0.74
    aughed
    0.70
    Activations Density 1.005%

    No Known Activations