© 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. 16852
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs indicating necessity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of necessity or lack thereof

    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
    uesday
    -0.75
    iple
    -0.69
    catentry
    -0.67
    cellence
    -0.61
    ccording
    -0.60
    atta
    -0.59
    imore
    -0.58
    kind
    -0.57
    ����
    -0.57
    Kind
    -0.57
    POSITIVE LOGITS
    lessly
    1.30
     anymore
    1.15
     nor
    0.86
    oppers
    0.79
     Apply
    0.79
     worry
    0.74
     fuss
    0.74
     bother
    0.74
     fret
    0.74
     necessarily
    0.71
    Activations Density 0.055%

    No Known Activations