© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 22861
    Prev
    Next
    INDEX
    Explanations

    situations or events involving challenges, criticism, or disciplinary actions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with backlash and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.61
     Lies
    -0.58
     Signal
    -0.58
    aple
    -0.58
    ete
    -0.57
     Canal
    -0.55
    aples
    -0.55
     Abs
    -0.55
     Paran
    -0.55
     aber
    -0.53
    POSITIVE LOGITS
     owing
    0.78
    xual
    0.73
    external
    0.71
    sha
    0.67
    back
    0.66
    unal
    0.66
    ón
    0.66
     setbacks
    0.65
     stemming
    0.65
    shell
    0.64
    Activations Density 0.291%

    No Known Activations