© 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. 7-RES-JB
    11. 17140
    Prev
    Next
    INDEX
    Explanations

    words related to taking action or moving forward

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "here comes" and related variations

    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
    ²¾
    -0.66
    lvl
    -0.66
    İ
    -0.65
    ģĸ
    -0.60
    ĵĺ
    -0.58
     redes
    -0.58
    çİĭ
    -0.57
    Loading
    -0.56
    Created
    -0.56
    entimes
    -0.55
    POSITIVE LOGITS
    ipop
    0.58
     Correctional
    0.51
     taxpayers
    0.50
     divert
    0.48
     Auditor
    0.48
     Fab
    0.48
     leaks
    0.46
     Eisen
    0.46
     Karl
    0.46
     Cass
    0.46
    Activations Density 1.113%

    No Known Activations