© 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. 18727
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific named concepts

    oai_token-act-pair · gpt-3.5-turbo

    specific cultural, social, and political references or phenomena

    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
    lain
    -0.74
     ..........
    -0.70
    ãģĻ
    -0.61
     Tropical
    -0.60
    abba
    -0.59
    ynthesis
    -0.59
    !.
    -0.58
    é¾įå
    -0.58
     ........
    -0.58
    }.
    -0.58
    POSITIVE LOGITS
     sighting
    0.78
     wat
    0.72
     enthusiast
    0.70
     experiences
    0.69
     theorist
    0.69
     experience
    0.67
     terminology
    0.65
     outing
    0.65
     sightings
    0.65
     outings
    0.63
    Activations Density 0.469%

    No Known Activations