© 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. 15153
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals involved in news stories, particularly related to incidents or events

    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
     conventions
    -0.75
     sophistic
    -0.72
    ournal
    -0.72
     mathemat
    -0.71
     economists
    -0.70
    Edited
    -0.69
     consultancy
    -0.65
     Galileo
    -0.65
     circular
    -0.65
     governors
    -0.64
    POSITIVE LOGITS
     Jr
    0.96
    anski
    0.93
    gren
    0.92
    zynski
    0.91
    zie
    0.89
    alez
    0.86
     aka
    0.86
    rano
    0.85
    inski
    0.85
    rouse
    0.84
    Activations Density 0.434%

    No Known Activations