© 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. 10-RES-JB
    11. 8054
    Prev
    Next
    INDEX
    Explanations

    adverbs or adjectives indicating intentionality or deliberate action

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with intentionality or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parables
    -0.79
    raph
    -0.69
    amac
    -0.68
    soon
    -0.67
    Stars
    -0.67
     Towns
    -0.65
    arious
    -0.65
     Protector
    -0.65
     Horizons
    -0.64
     Rating
    -0.64
    POSITIVE LOGITS
     mislead
    1.00
     sabot
    1.00
     dece
    1.00
     misrepresent
    0.99
     misleading
    0.98
     misled
    0.97
     obfusc
    0.97
     fals
    0.95
     omitted
    0.95
     deceive
    0.91
    Activations Density 0.045%

    No Known Activations