© 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. 1-RES-JB
    11. 16813
    Prev
    Next
    INDEX
    Explanations

    the mention of cranes

    oai_token-act-pair · gpt-3.5-turbo

    references to construction-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.78
    essions
    -0.77
    VERTISEMENT
    -0.67
    SON
    -0.66
    ospons
    -0.65
    lav
    -0.65
    imei
    -0.63
    sequently
    -0.63
    orge
    -0.63
    nown
    -0.60
    POSITIVE LOGITS
    amina
    0.75
    jer
    0.67
     ILCS
    0.67
    burg
    0.64
    ulz
    0.63
    代
    0.63
     mill
    0.63
    ä½ľ
    0.60
    zb
    0.59
     mills
    0.59
    Activations Density 0.000%

    No Known Activations