© 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. 0-RES-JB
    11. 22365
    Prev
    Next
    INDEX
    Explanations

    instances of endorsement or support

    oai_token-act-pair · gpt-3.5-turbo

    the term "endorsed" and its variations, indicating agreement or support for a person, idea, or initiative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gal
    -0.68
    unit
    -0.68
     Wei
    -0.68
    oir
    -0.65
     holes
    -0.64
     drill
    -0.64
     Qin
    -0.63
     Tsukuyomi
    -0.63
    net
    -0.63
     guessing
    -0.62
    POSITIVE LOGITS
     endorsed
    3.39
     endorse
    3.23
     endorsing
    2.84
     endorsement
    2.63
     endorsements
    2.43
     endors
    2.16
    orses
    1.67
     disav
    1.39
     condone
    1.38
     repud
    1.22
    Activations Density 0.022%

    No Known Activations