© 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. 4-RES-JB
    11. 14788
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "endorf"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'endor' and related mentions of endorsements or supporters

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

    No Comments

    Negative Logits
    istical
    -0.83
    onyms
    -0.82
    ophe
    -0.75
    ues
    -0.73
    box
    -0.72
    eenth
    -0.71
    Catholic
    -0.71
    tons
    -0.71
    boxes
    -0.70
     Rite
    -0.70
    POSITIVE LOGITS
     McF
    1.04
    adden
    0.83
    ffer
    0.82
    FE
    0.81
    ff
    0.73
    arlane
    0.70
    ENCE
    0.70
    endor
    0.69
    FF
    0.67
    ENSE
    0.65
    Activations Density 0.027%

    No Known Activations