© 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. 6-RES-JB
    11. 19812
    Prev
    Next
    INDEX
    Explanations

    verbs related to persuasion or influence

    oai_token-act-pair · gpt-3.5-turbo

    words associated with manipulation and persuasion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     effected
    -0.73
    externalActionCode
    -0.71
     Skydragon
    -0.68
     surg
    -0.65
    icut
    -0.62
     footprint
    -0.60
    hattan
    -0.60
     closely
    -0.59
    anwhile
    -0.58
     photograp
    -0.58
    POSITIVE LOGITS
     excuses
    0.80
     suggestions
    0.79
     assurances
    0.76
     virtues
    0.74
    ATURES
    0.72
     opinions
    0.72
     praise
    0.70
    eers
    0.69
     endorsements
    0.69
     Parables
    0.68
    Activations Density 0.190%

    No Known Activations