© 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. 0-RES-JB
    11. 17010
    Prev
    Next
    INDEX
    Explanations

    dates in the format of month/day/year with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    numerical references, particularly related to scoring or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cheers
    -0.68
     biography
    -0.67
     knob
    -0.66
     thumbs
    -0.65
     Musk
    -0.64
     stare
    -0.62
     blame
    -0.62
    ãĤ©
    -0.61
     grop
    -0.60
     greet
    -0.60
    POSITIVE LOGITS
    12
    3.18
    13
    2.30
    11
    2.29
    14
    2.18
    10
    2.13
    16
    2.06
    15
    2.04
    18
    1.97
    17
    1.91
    1200
    1.84
    Activations Density 0.026%

    No Known Activations