© 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. 10641
    Prev
    Next
    INDEX
    Explanations

    terms related to morphological changes or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to morphology and its variations

    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
    utherland
    -0.78
    FUL
    -0.76
    ãĥĨãĤ£
    -0.76
    âĸ¬
    -0.75
    HI
    -0.71
    ×Ļ
    -0.67
    ORED
    -0.64
    vier
    -0.64
     Jamaica
    -0.63
    ILLE
    -0.63
    POSITIVE LOGITS
    orph
    1.34
    ophon
    1.12
    anism
    0.89
    ological
    0.88
    thal
    0.87
    oreal
    0.86
    odi
    0.83
    icides
    0.82
    morph
    0.81
    laus
    0.81
    Activations Density 0.013%

    No Known Activations