© 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. 10-RES-JB
    11. 12275
    Prev
    Next
    INDEX
    Explanations

    phrases related to being lost or trapped in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of being "lost" in various contexts or situations

    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
    saf
    -0.69
    ok
    -0.67
    available
    -0.65
    hey
    -0.65
    owned
    -0.65
    allowed
    -0.65
    leck
    -0.64
     Fighters
    -0.64
    Voice
    -0.63
    provided
    -0.62
    POSITIVE LOGITS
     obscurity
    1.21
     limbo
    1.21
     knots
    0.93
     mud
    0.92
     fog
    0.91
     secrecy
    0.90
     mystery
    0.89
    effic
    0.88
     amber
    0.87
     bureaucracy
    0.86
    Activations Density 0.117%

    No Known Activations