© 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. 9-RES-JB
    11. 18524
    Prev
    Next
    INDEX
    Explanations

    proper names and titles within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to sports and possibly academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.71
    ailability
    -0.66
    jri
    -0.60
    llor
    -0.60
    ancial
    -0.59
     sqor
    -0.59
    ittance
    -0.58
     Yon
    -0.57
     vou
    -0.57
    lihood
    -0.55
    POSITIVE LOGITS
    phia
    0.94
    ops
    0.81
    igham
    0.72
    auga
    0.72
    eph
    0.71
    ennis
    0.68
    aed
    0.67
    oche
    0.66
    gio
    0.66
    ophy
    0.65
    Activations Density 0.217%

    No Known Activations