© 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. 4-RES-JB
    11. 2827
    Prev
    Next
    INDEX
    Explanations

    phrases related to false information or accusations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to false accusations or misleading claims

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

    No Comments

    Negative Logits
     enthus
    -0.76
     verbs
    -0.72
     willingness
    -0.71
     commandments
    -0.70
     methods
    -0.70
    ger
    -0.70
     reservations
    -0.69
    uese
    -0.69
     substitution
    -0.68
     reactions
    -0.67
    POSITIVE LOGITS
     detonated
    0.82
     produced
    0.79
     represented
    0.78
     housed
    0.78
     transitioned
    0.77
     scratched
    0.76
     addressed
    0.75
     regenerate
    0.75
     modeled
    0.75
    ãĤ©
    0.75
    Activations Density 0.058%

    No Known Activations