© 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. 8-RES-JB
    11. 22622
    Prev
    Next
    INDEX
    Explanations

    words related to pin-related items or activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "pin" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.98
    earch
    -0.69
     Rover
    -0.69
    IGH
    -0.68
    mberg
    -0.68
     behav
    -0.68
     HELP
    -0.67
    á
    -0.67
     LAT
    -0.66
     Ways
    -0.65
    POSITIVE LOGITS
    ning
    1.27
    ochet
    1.18
    ching
    1.07
    ball
    1.05
    ned
    1.02
    ched
    0.94
    wheel
    0.91
    keye
    0.89
    strip
    0.86
    cher
    0.86
    Activations Density 0.033%

    No Known Activations