© 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. 18448
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility like 'may' and 'can'

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs that express possibility or uncertainty

    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
    />
    -0.69
     Guth
    -0.66
    Īè
    -0.63
     BaseType
    -0.57
     Divinity
    -0.55
     Buddh
    -0.55
     Krish
    -0.55
     race
    -0.54
    ginx
    -0.54
     sugg
    -0.53
    POSITIVE LOGITS
     alike
    0.74
     AGA
    0.73
    achi
    0.69
    anton
    0.68
    AI
    0.67
    rite
    0.67
    hetamine
    0.66
    gal
    0.64
    anan
    0.64
    ILA
    0.64
    Activations Density 0.412%

    No Known Activations