© 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. 11-RES-JB
    11. 7820
    Prev
    Next
    INDEX
    Explanations

    statements about the potential impact of various actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases discussing the effects and consequences of various actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsk
    -0.76
     Guilty
    -0.74
    opter
    -0.69
     Style
    -0.68
    fuck
    -0.65
     Puzzles
    -0.60
    english
    -0.60
     Franch
    -0.60
     Requirements
    -0.60
    dar
    -0.60
    POSITIVE LOGITS
     negligible
    1.39
     minimal
    1.22
     immense
    1.20
     profound
    1.19
     immediate
    1.11
     considerable
    1.11
     enormous
    1.10
     substantial
    1.10
     undeniable
    1.05
     measurable
    1.03
    Activations Density 0.194%

    No Known Activations