© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 11394
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating the start of an action or a change in status

    oai_token-act-pair · gpt-3.5-turbo

    emotional states and expressions of perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.76
    bred
    -0.64
     premier
    -0.62
     Suc
    -0.61
     Surprise
    -0.61
     abst
    -0.60
     retiring
    -0.59
     Aus
    -0.59
     congratulated
    -0.59
    esides
    -0.58
    POSITIVE LOGITS
     sporadic
    0.75
     anew
    0.71
     patterns
    0.67
    ilial
    0.66
     problems
    0.63
    hing
    0.63
     worrisome
    0.62
    alysed
    0.62
     uncontroll
    0.62
     clearer
    0.62
    Activations Density 0.152%

    No Known Activations