© 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. 2586
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to a specific time frame ("within") and indicates greater activation for occurrences closer to the number 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "within" followed by a number

    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
    vous
    -0.76
    di
    -0.73
     Genie
    -0.73
    nt
    -0.69
    mat
    -0.66
    mir
    -0.64
    lace
    -0.63
    ln
    -0.63
    bas
    -0.62
    Published
    -0.62
    POSITIVE LOGITS
    ieth
    0.98
    ¥ŀ
    0.89
    ĵĺ
    0.87
    ħĭ
    0.83
    avorite
    0.83
    imore
    0.82
     Survive
    0.81
    ĨĴ
    0.80
    ruciating
    0.79
    htaking
    0.77
    Activations Density 0.027%

    No Known Activations