© 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. 23662
    Prev
    Next
    INDEX
    Explanations

    terms related to investigation and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to analysis and examination processes

    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
     Blacks
    -0.60
    letters
    -0.59
    Torrent
    -0.59
     offending
    -0.59
     trailing
    -0.58
    mber
    -0.57
     Rh
    -0.57
    adra
    -0.56
     beginnings
    -0.56
    Layout
    -0.56
    POSITIVE LOGITS
     separately
    1.09
    ĸļ
    1.04
     individually
    0.96
     electronically
    0.90
     thoroughly
    0.90
     by
    0.90
     anew
    0.89
     extensively
    0.88
     administr
    0.87
    ividually
    0.85
    Activations Density 0.183%

    No Known Activations