© 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. 2-RES-JB
    11. 20731
    Prev
    Next
    INDEX
    Explanations

    names of specific characters and locations within a fantasy world

    oai_token-act-pair · gpt-3.5-turbo

    references to the fictional land of Westeros and its inhabitants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obbies
    -0.74
    ees
    -0.70
    umbai
    -0.69
    trak
    -0.69
    Reviewer
    -0.68
    yout
    -0.67
    ysis
    -0.65
    cision
    -0.65
    iasis
    -0.62
    izu
    -0.61
    POSITIVE LOGITS
     Lann
    1.52
     Wester
    1.32
     Thrones
    1.07
     Targ
    1.02
    lund
    0.93
     Stark
    0.93
    ullivan
    0.85
     Bolton
    0.84
     Bundy
    0.82
    gaard
    0.81
    Activations Density 0.018%

    No Known Activations