© 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. 21463
    Prev
    Next
    INDEX
    Explanations

    words related to therapy or treatment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to thermal properties and therapies

    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
     duty
    -0.67
     Elk
    -0.65
    ELS
    -0.65
    urger
    -0.63
     broken
    -0.62
     Pearce
    -0.59
     Starr
    -0.59
     strings
    -0.58
     dollars
    -0.58
     Hurt
    -0.58
    POSITIVE LOGITS
    apist
    1.75
    apy
    1.57
    ape
    1.41
    mia
    1.33
    mic
    1.26
    mop
    1.24
    mite
    1.20
    mal
    1.19
    mid
    1.15
    mos
    1.12
    Activations Density 0.058%

    No Known Activations