© 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. 7-RES-JB
    11. 3883
    Prev
    Next
    INDEX
    Explanations

    phrases indicating being lost or confused in a context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "lost in."

    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
    XY
    -0.76
    DIT
    -0.75
    IOR
    -0.75
    Trigger
    -0.71
    âĶĢâĶĢâĶĢâĶĢ
    -0.70
    OST
    -0.68
    UID
    -0.67
    CLUD
    -0.66
     empowered
    -0.65
    iola
    -0.65
    POSITIVE LOGITS
     obscurity
    0.94
     abstraction
    0.77
     shuffle
    0.77
     Mania
    0.74
     Atlantis
    0.72
     Clouds
    0.71
     Translation
    0.70
     imagination
    0.70
     laughter
    0.70
     Madness
    0.70
    Activations Density 0.122%

    No Known Activations