© 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. 17109
    Prev
    Next
    INDEX
    Explanations

    proper nouns (names of people, organizations, etc.) and specific keywords related to instructions or preparations

    oai_token-act-pair · gpt-3.5-turbo

    entities related to specific organizations, groups, or characteristics within societal contexts

    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
    onet
    -0.87
    DragonMagazine
    -0.74
    ailability
    -0.72
    ocious
    -0.71
    geries
    -0.71
    maxwell
    -0.67
    arial
    -0.67
    raints
    -0.66
    ategory
    -0.66
    cluding
    -0.64
    POSITIVE LOGITS
     deems
    1.24
     deem
    1.00
     sorely
    0.87
     lacked
    0.85
     couldn
    0.84
     refers
    0.81
     considers
    0.81
     forgot
    0.81
     overlook
    0.80
     could
    0.80
    Activations Density 0.337%

    No Known Activations