© 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. 10-RES-JB
    11. 898
    Prev
    Next
    INDEX
    Explanations

    instances where things are physically or metaphorically open

    oai_token-act-pair · gpt-3.5-turbo

    references to doors or openings, both literal and metaphorical

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.78
     endors
    -0.61
     Voice
    -0.60
    ivan
    -0.58
    ahon
    -0.58
    Fan
    -0.56
    Ranked
    -0.56
    von
    -0.56
    member
    -0.56
     metals
    -0.55
    POSITIVE LOGITS
    ahead
    0.80
    ource
    0.80
    oresc
    0.77
    iltr
    0.73
    doors
    0.73
     pores
    0.73
     doors
    0.72
     Doors
    0.70
     indefinitely
    0.69
     minded
    0.69
    Activations Density 0.064%

    No Known Activations