© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 3851
    Prev
    Next
    INDEX
    Explanations

    code snippets or technical terms related to programming and coding

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and identifiers related to programming or computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conclud
    -0.65
     headlined
    -0.64
    enegger
    -0.63
     MacArthur
    -0.62
     AFP
    -0.62
    oulos
    -0.61
     ÂŃ
    -0.60
     Beir
    -0.60
     endowed
    -0.57
    theless
    -0.57
    POSITIVE LOGITS
    erc
    0.82
    ax
    0.73
    rop
    0.70
    Spawn
    0.70
    Bot
    0.69
    Mech
    0.69
    Serv
    0.69
    Setup
    0.68
    Cat
    0.67
    ute
    0.67
    Activations Density 0.521%

    No Known Activations