© 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. 24135
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurements and financial considerations

    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
     Guer
    -0.71
     confer
    -0.69
    terday
    -0.66
     anecd
    -0.65
     contempor
    -0.64
     Du
    -0.61
     Companion
    -0.61
     daddy
    -0.60
    LT
    -0.60
    CU
    -0.60
    POSITIVE LOGITS
    asses
    1.04
    ishers
    1.03
    uments
    1.02
    ables
    0.99
    lems
    0.98
    ees
    0.97
    keys
    0.96
    als
    0.96
    ivities
    0.96
    ieties
    0.94
    Activations Density 0.442%

    No Known Activations