© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19267
    Prev
    Next
    INDEX
    Explanations

    terms related to consequences or impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discussions and assessments of consequences and responsibilities in various contexts

    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
    poon
    -0.70
    !,
    -0.63
    .$
    -0.63
    dit
    -0.62
    !.
    -0.61
    +.
    -0.60
    cot
    -0.59
    isse
    -0.58
    intend
    -0.56
    iolet
    -0.56
    POSITIVE LOGITS
     varies
    1.02
     remains
    0.86
     arises
    0.83
     differs
    0.83
     becomes
    0.79
     is
    0.77
     depends
    0.76
     isn
    0.75
     seems
    0.75
     hasn
    0.74
    Activations Density 0.377%

    No Known Activations