© 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. 8-RES-JB
    11. 918
    Prev
    Next
    INDEX
    Explanations

    verbs indicating a change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "become" and its variations, indicating a focus on transformation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inately
    -0.73
    ength
    -0.72
    inarily
    -0.71
    idth
    -0.67
     Cran
    -0.66
    astern
    -0.63
    brow
    -0.63
    merga
    -0.63
    erity
    -0.62
    ramid
    -0.62
    POSITIVE LOGITS
     extinct
    1.08
     obsolete
    1.04
     clearer
    0.92
     entangled
    0.91
     irrelevant
    0.90
     commonplace
    0.88
     indistinguishable
    0.86
     evident
    0.85
     increasingly
    0.85
     apparent
    0.84
    Activations Density 0.057%

    No Known Activations