© 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. 11-RES-JB
    11. 17640
    Prev
    Next
    INDEX
    Explanations

    phrases related to the current or present time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a current state or ongoing situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.69
    efe
    -0.67
    arag
    -0.65
     Secondly
    -0.63
    ved
    -0.63
    lier
    -0.60
    -+
    -0.59
    azo
    -0.59
    Secondly
    -0.58
    acist
    -0.58
    POSITIVE LOGITS
     anyway
    0.92
     though
    0.85
     purposes
    0.85
     suffice
    0.83
     anyways
    0.81
    adays
    0.70
     onward
    0.66
     onwards
    0.66
    here
    0.63
     sake
    0.63
    Activations Density 0.085%

    No Known Activations