© 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. 10-RES-JB
    11. 16231
    Prev
    Next
    INDEX
    Explanations

    names of organizations or groups with the prefix "und"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fund" or related terms indicating financial support or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.84
    ======
    -0.65
    utic
    -0.63
     outwe
    -0.63
     losers
    -0.61
     adv
    -0.60
    grading
    -0.59
     foul
    -0.58
     bluff
    -0.57
     majors
    -0.56
    POSITIVE LOGITS
    efined
    1.06
    rums
    1.05
    erest
    1.03
    emonium
    0.99
    ecided
    0.98
    erer
    0.97
    ocumented
    0.97
    heit
    0.96
    lich
    0.93
    reth
    0.93
    Activations Density 0.019%

    No Known Activations