© 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. 10-RES-JB
    11. 12360
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of individuals, especially with varying lengths

    oai_token-act-pair · gpt-3.5-turbo

    letters and corresponding character frequencies in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.66
     respectively
    -0.64
     elig
    -0.59
     cradle
    -0.58
     academ
    -0.57
     representation
    -0.56
     groove
    -0.55
     Ascension
    -0.55
     responsible
    -0.55
     magnification
    -0.54
    POSITIVE LOGITS
    hardt
    1.15
    hart
    1.11
    stein
    1.11
    linger
    1.07
    ston
    0.99
    heimer
    0.98
    quist
    0.97
    heim
    0.97
    bert
    0.97
    rich
    0.97
    Activations Density 0.110%

    No Known Activations