© 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. 3720
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurement units

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and character strings related to names and identifiers

    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
     Aber
    -0.83
    ESCO
    -0.78
     Unc
    -0.77
     Alexander
    -0.73
     Beetle
    -0.73
     ALE
    -0.72
    Alexander
    -0.72
     Edison
    -0.70
     Jones
    -0.70
     Bert
    -0.69
    POSITIVE LOGITS
    +++
    0.82
     plur
    0.78
    atum
    0.74
    RP
    0.73
    zbollah
    0.73
    mus
    0.73
    utt
    0.73
     sidx
    0.72
    jiang
    0.72
    WP
    0.69
    Activations Density 0.412%

    No Known Activations