© 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. 11693
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Akak" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or name

    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
    Ö¼
    -0.81
    ãĤ¡
    -0.70
    ãĤ£
    -0.67
    drops
    -0.65
    builders
    -0.65
     ILCS
    -0.63
     pint
    -0.63
     Collider
    -0.62
     dividend
    -0.62
    ORPG
    -0.61
    POSITIVE LOGITS
    unin
    1.24
    arak
    1.13
    umar
    1.11
    ota
    1.02
    shi
    0.98
    istani
    0.97
    ansas
    0.97
    rish
    0.96
    iri
    0.96
    arta
    0.95
    Activations Density 0.034%

    No Known Activations