© 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. 11-RES-JB
    11. 17647
    Prev
    Next
    INDEX
    Explanations

    phrases containing comparisons or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating alternatives or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upper
    -0.73
    Marginal
    -0.72
    fifth
    -0.72
    iple
    -0.69
    SON
    -0.67
    meric
    -0.67
    enser
    -0.66
    breakers
    -0.65
    third
    -0.65
    ledged
    -0.65
    POSITIVE LOGITS
     relying
    1.26
     focusing
    1.25
     wasting
    1.19
     risking
    1.16
     letting
    1.16
     worrying
    1.12
     acknowledging
    1.07
     opting
    1.07
     apologizing
    1.06
     concentrating
    1.06
    Activations Density 0.060%

    No Known Activations