© 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. 18471
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions or statements made by a specific person

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "he"

    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
    noon
    -0.84
    etheless
    -0.75
    acters
    -0.72
    rocket
    -0.71
    evidence
    -0.64
    Operation
    -0.64
    selection
    -0.60
     totality
    -0.60
     fractions
    -0.60
    lihood
    -0.57
    POSITIVE LOGITS
     said
    1.43
     wrote
    1.33
     says
    1.24
     joked
    1.17
     exclaimed
    1.15
    said
    1.14
     tweeted
    1.14
     explained
    1.13
     told
    1.12
     replied
    1.08
    Activations Density 0.065%

    No Known Activations