© 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. 20543
    Prev
    Next
    INDEX
    Explanations

    references to popular franchises

    oai_token-act-pair · gpt-3.5-turbo

    references to film and television franchises

    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
     Azerbai
    -0.72
     "$:/
    -0.71
     Ivory
    -0.71
    camp
    -0.70
     diary
    -0.68
     Gab
    -0.68
     SPD
    -0.68
     Eagle
    -0.68
     Sie
    -0.67
    Gab
    -0.67
    POSITIVE LOGITS
     franchises
    2.55
     reboot
    1.39
     franchise
    1.31
     relocation
    1.26
     franch
    1.22
     sequels
    1.19
    ranch
    1.19
     relocate
    1.17
     recognizable
    1.13
     universes
    1.10
    Activations Density 0.065%

    No Known Activations