© 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. 8-RES-JB
    11. 18576
    Prev
    Next
    INDEX
    Explanations

    the word "test" with different contexts and forms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "test" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignt
    -0.77
    theless
    -0.73
    vernment
    -0.71
    leans
    -0.64
    ĺħ
    -0.63
    resent
    -0.63
    etheless
    -0.62
     Rove
    -0.62
    taboola
    -0.61
    VIDIA
    -0.60
    POSITIVE LOGITS
    osterone
    1.52
    imony
    1.45
    imon
    1.10
    icles
    1.08
    icular
    1.08
    udo
    1.07
    icle
    1.07
    ifies
    0.97
    aments
    0.87
    su
    0.87
    Activations Density 0.031%

    No Known Activations