© 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. 0-RES-JB
    11. 495
    Prev
    Next
    INDEX
    Explanations

    references to things that were previously known by another name

    oai_token-act-pair · gpt-3.5-turbo

    references to entities with prior names or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blizz
    -0.65
    opl
    -0.63
     Logged
    -0.61
    Loading
    -0.55
    Suggest
    -0.53
    ...
    -0.53
     ups
    -0.53
    Sign
    -0.53
    ----------------------------------------------------------------
    -0.53
    oster
    -0.53
    POSITIVE LOGITS
     formerly
    3.67
    formerly
    2.18
     previously
    1.84
     hitherto
    1.80
     Previously
    1.33
     originally
    1.31
     former
    1.30
     Former
    1.26
    Previously
    1.15
     vacated
    1.14
    Activations Density 0.012%

    No Known Activations