© 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. 6-RES-JB
    11. 18833
    Prev
    Next
    INDEX
    Explanations

    mentions of characters in a story or narrative

    oai_token-act-pair · gpt-3.5-turbo

    references to characters in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Effective
    -0.67
    Accessory
    -0.66
    LOCK
    -0.65
    VERTIS
    -0.65
     Wass
    -0.59
    ctr
    -0.59
    gard
    -0.59
     Kop
    -0.58
     Dhabi
    -0.58
     Kremlin
    -0.58
    POSITIVE LOGITS
    acters
    1.39
    istically
    0.99
    istics
    0.92
    aws
    0.76
    hips
    0.74
     characters
    0.73
     Characters
    0.72
     assassinate
    0.72
    aces
    0.72
    hots
    0.71
    Activations Density 0.025%

    No Known Activations