© 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. 0-RES-JB
    11. 23315
    Prev
    Next
    INDEX
    Explanations

    phrases related to fantasy, especially in the context of fantasy football

    oai_token-act-pair · gpt-3.5-turbo

    references to fantasy themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Luxem
    -0.74
     Coco
    -0.74
     Tiff
    -0.72
     awa
    -0.69
     Alic
    -0.67
     Constantin
    -0.66
     disadvant
    -0.66
    afety
    -0.65
     Moose
    -0.65
    ãĥķãĤ©
    -0.65
    POSITIVE LOGITS
    iron
    0.79
    assion
    0.78
    raped
    0.76
    eyed
    0.75
    cycl
    0.72
    +(
    0.71
    rarily
    0.70
    efficient
    0.70
    vard
    0.70
    govtrack
    0.70
    Activations Density 0.000%

    No Known Activations