© 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. 9894
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone having control or possession over something

    oai_token-act-pair · gpt-3.5-turbo

    references to power or control held by specific groups or individuals

    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
     abbrevi
    -0.58
     doubling
    -0.57
    apor
    -0.56
    redo
    -0.55
     positives
    -0.53
     trending
    -0.52
    SEE
    -0.52
    anned
    -0.50
    atten
    -0.50
     confirming
    -0.49
    POSITIVE LOGITS
     of
    0.91
    OF
    0.75
    hip
    0.75
    rils
    0.73
    lust
    0.72
    ¿
    0.71
     Of
    0.71
    adle
    0.68
     OF
    0.67
    linger
    0.67
    Activations Density 0.058%

    No Known Activations