© 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. 9-RES-JB
    11. 18573
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and past tense verbs related to actions

    oai_token-act-pair · gpt-3.5-turbo

    pronouns, particularly focusing on characters and their actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.83
    ogue
    -0.73
    arthed
    -0.73
    catentry
    -0.72
    aunch
    -0.67
    uesday
    -0.66
    opolis
    -0.63
    ruciating
    -0.62
    retty
    -0.62
     Globe
    -0.61
    POSITIVE LOGITS
    'll
    1.34
    'd
    1.17
    're
    0.98
     ought
    0.94
     could
    0.94
     SHOULD
    0.92
    've
    0.91
     misunder
    0.91
     forgot
    0.90
     would
    0.89
    Activations Density 0.220%

    No Known Activations