© 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. 9-RES-JB
    11. 18633
    Prev
    Next
    INDEX
    Explanations

    words related to incorrect information or judgments

    oai_token-act-pair · gpt-3.5-turbo

    negative assessments or criticisms of concepts and arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interrupted
    -0.96
     downed
    -0.72
    inder
    -0.67
    rolled
    -0.67
    runners
    -0.65
    illas
    -0.64
    gins
    -0.62
    rollers
    -0.62
    hens
    -0.61
     disbanded
    -0.60
    POSITIVE LOGITS
     insofar
    0.86
     simplistic
    0.84
    headed
    0.82
     analogy
    0.76
     extrap
    0.76
     rhetorical
    0.75
    ctive
    0.75
     empir
    0.75
     underest
    0.75
     logic
    0.74
    Activations Density 0.211%

    No Known Activations