© 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. 4-RES-JB
    6. 8492
    Prev
    Next
    INDEX
    Explanations

    words related to optimization and performance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology, automation, and optimization

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

    No Comments

    Negative Logits
    theless
    -1.08
    terday
    -0.82
     shroud
    -0.75
     tune
    -0.72
     coli
    -0.70
     delight
    -0.68
    çĦ
    -0.66
    OHN
    -0.66
     americ
    -0.65
    olson
    -0.64
    POSITIVE LOGITS
    emark
    0.94
    ename
    0.92
    rav
    0.92
    icit
    0.90
    iliated
    0.89
    acia
    0.89
    amation
    0.89
    phies
    0.88
    ensing
    0.88
    icion
    0.87
    Activations Density 0.137%

    No Known Activations