© 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. 2-RES-JB
    11. 8340
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "ask" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "ask" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     customary
    -0.68
    BER
    -0.66
    pite
    -0.65
     subsid
    -0.63
    birth
    -0.63
    nerg
    -0.61
     disproportionate
    -0.60
    bably
    -0.60
    iltration
    -0.57
    berman
    -0.57
    POSITIVE LOGITS
    atchewan
    1.21
    ask
    1.19
    edIn
    1.13
    ansas
    1.01
    oln
    0.98
    ings
    0.96
    atoon
    0.93
    furt
    0.92
    erville
    0.91
    annel
    0.91
    Activations Density 0.006%

    No Known Activations