© 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. 22538
    Prev
    Next
    INDEX
    Explanations

    references to the company IBM

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company IBM

    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
     Gun
    -0.72
     Turkey
    -0.70
    skin
    -0.70
    Turkey
    -0.70
    Turkish
    -0.68
     shooting
    -0.67
    gun
    -0.67
    Dest
    -0.67
    Gun
    -0.66
     Turkish
    -0.64
    POSITIVE LOGITS
     IBM
    3.53
    IB
    1.64
     Atari
    1.40
     Macintosh
    1.32
     Turing
    1.30
     Watson
    1.29
     Unix
    1.29
     IEEE
    1.20
     BlackBerry
    1.20
     Edison
    1.15
    Activations Density 0.026%

    No Known Activations