© 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. 23438
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or alternative possibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express uncertainty or conditionality

    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
    ãĥĸ
    -0.75
    schild
    -0.71
     Manufacturer
    -0.65
    WB
    -0.64
    ãĥ¼ãĥ³
    -0.64
    ãĥ³ãĤ¸
    -0.60
    anging
    -0.59
    bush
    -0.59
    ailable
    -0.59
    ãĥĩãĤ£
    -0.58
    POSITIVE LOGITS
     happens
    0.75
     develops
    0.70
    uthor
    0.67
     else
    0.65
    ipop
    0.64
    ught
    0.64
     proves
    0.63
     regress
    0.63
    icious
    0.63
     interven
    0.62
    Activations Density 0.041%

    No Known Activations