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

    Neuronpedia

    Jacobian LensNEW
    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. 20818
    Prev
    Next
    INDEX
    Explanations

    proposals or suggestions mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "to" in various contexts and proposals

    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
    furt
    -0.70
     glances
    -0.69
     Bened
    -0.68
    points
    -0.67
    mails
    -0.66
     moments
    -0.65
    horn
    -0.65
    reports
    -0.64
    thing
    -0.64
    need
    -0.63
    POSITIVE LOGITS
     revise
    1.23
     promote
    1.19
     explore
    1.16
     conserve
    1.14
     communicate
    1.14
     establish
    1.13
     classify
    1.13
     eliminate
    1.13
     appease
    1.13
     create
    1.12
    Activations Density 0.253%

    No Known Activations