© 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. 14750
    Prev
    Next
    INDEX
    Explanations

    words related to changes or actions being carried out on something

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to actions or states of being

    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
     includ
    -0.83
    DEF
    -0.73
    fit
    -0.65
    RB
    -0.60
    reach
    -0.58
     tune
    -0.57
    orest
    -0.57
     Kov
    -0.57
     suffix
    -0.56
    udicrous
    -0.56
    POSITIVE LOGITS
    uled
    0.87
    iovascular
    0.81
    own
    0.79
    ased
    0.77
    igion
    0.77
    emption
    0.75
    ience
    0.75
    opsis
    0.74
    iac
    0.73
    oll
    0.73
    Activations Density 0.015%

    No Known Activations