© 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. 2-RES-JB
    11. 836
    Prev
    Next
    INDEX
    Explanations

    the syllable "raf" within words

    oai_token-act-pair · gpt-4-turbo

    names or terms related to specific person

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual's name or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MacArthur
    -0.85
     Mustang
    -0.73
     Avalon
    -0.70
     Newton
    -0.70
     Townsend
    -0.67
     Casey
    -0.67
     Pompe
    -0.67
     Cors
    -0.66
     Gravity
    -0.65
     Parenthood
    -0.65
    POSITIVE LOGITS
    raf
    1.06
    ischer
    0.92
    ÃŃa
    0.92
    archy
    0.89
    cia
    0.88
    ringe
    0.87
    enda
    0.86
    azine
    0.85
    quez
    0.84
    ugal
    0.84
    Activations Density 0.011%

    No Known Activations