© 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. 8-RES-JB
    11. 18713
    Prev
    Next
    INDEX
    Explanations

    words related to the size or magnitude of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the magnitude or extent of issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.70
    olkien
    -0.69
    ategor
    -0.66
     Advertisement
    -0.61
    issy
    -0.60
    Eva
    -0.58
    ocally
    -0.58
     Ago
    -0.56
    INO
    -0.56
    isse
    -0.55
    POSITIVE LOGITS
     of
    1.06
     thereof
    1.03
    iest
    1.02
    of
    0.80
    liest
    0.80
    iness
    0.80
    fulness
    0.79
    lessness
    0.79
     inherent
    0.77
     OF
    0.76
    Activations Density 0.320%

    No Known Activations