© 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. 3-RES-JB
    11. 7061
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a large quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sheer" along with its use in various contexts emphasizing magnitude or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.90
    afort
    -0.77
    artments
    -0.73
     prosec
    -0.73
     reper
    -0.72
    ACP
    -0.69
     Surv
    -0.68
    lict
    -0.67
     inspected
    -0.67
    quartered
    -0.67
    POSITIVE LOGITS
     sheer
    0.87
     coincidence
    0.82
     volume
    0.81
    tons
    0.80
     quantity
    0.78
     quantities
    0.77
    ane
    0.74
    ãĤ¨ãĥ«
    0.70
     numbers
    0.70
     numerical
    0.69
    Activations Density 0.004%

    No Known Activations