© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9354
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions or impactful situations

    oai_token-act-pair · gpt-3.5-turbo

    short words or fragments that can indicate discontent or distress

    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
     submitting
    -0.75
     committing
    -0.68
     submission
    -0.68
     complying
    -0.67
     confess
    -0.67
     drafting
    -0.65
     donating
    -0.65
     signing
    -0.65
     implementing
    -0.64
     affirmative
    -0.63
    POSITIVE LOGITS
    ounded
    1.32
    inged
    1.10
    irled
    1.09
    alysed
    1.06
    eared
    1.03
    acerb
    1.01
    olved
    1.01
    elled
    1.01
    fired
    1.00
    ersed
    1.00
    Activations Density 0.110%

    No Known Activations