© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38
    Prev
    Next
    INDEX
    Explanations

    phrases indicating likelihood or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate certainty or speculation

    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
    ĸļ
    -1.26
    ãĤ©
    -0.86
    ãĥ¯ãĥ³
    -0.72
    æĪ¦
    -0.65
    regular
    -0.64
    eret
    -0.64
     Deaths
    -0.62
    ãĤ¸
    -0.62
    è£
    -0.61
     Turns
    -0.61
    POSITIVE LOGITS
     conceivable
    1.41
     unlikely
    1.41
     doubtful
    1.30
     likely
    1.22
     TBD
    1.16
     unclear
    1.14
     feasible
    1.14
     plausible
    1.10
     possible
    1.09
     uncertain
    1.08
    Activations Density 0.279%

    No Known Activations