© 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. 18453
    Prev
    Next
    INDEX
    Explanations

    capital letters

    oai_token-act-pair · gpt-3.5-turbo

    letters and specific characters in the text

    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
     debit
    -0.67
    çĶ°
    -0.66
    00007
    -0.64
     Scion
    -0.61
     Mub
    -0.60
     elig
    -0.59
    éĹĺ
    -0.58
     Hurricanes
    -0.57
     Totem
    -0.56
     Chiefs
    -0.55
    POSITIVE LOGITS
    ilus
    0.91
    urnal
    0.83
    obic
    0.82
    otropic
    0.80
    aceae
    0.79
    Henry
    0.74
    igen
    0.72
    ical
    0.72
    alf
    0.71
    oric
    0.71
    Activations Density 0.061%

    No Known Activations