© 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. 11-RES-JB
    11. 19297
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of specific entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inventory
    -0.67
    ctive
    -0.67
    ionics
    -0.67
    retty
    -0.67
    athy
    -0.66
    erald
    -0.66
     Guys
    -0.63
     Puzzles
    -0.63
    lex
    -0.60
     Passive
    -0.60
    POSITIVE LOGITS
     supposed
    1.11
     purportedly
    1.10
     supposedly
    1.09
     incidentally
    1.07
     subsequently
    1.04
     allegedly
    1.01
     purported
    0.98
     ostensibly
    0.97
     overseen
    0.92
     besie
    0.91
    Activations Density 0.164%

    No Known Activations