© 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. 7-RES-JB
    11. 16763
    Prev
    Next
    INDEX
    Explanations

    age ranges

    oai_token-act-pair · gpt-3.5-turbo

    numerical ranges and statistics related to age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     è£ıè
    -0.74
    regor
    -0.70
    ophen
    -0.70
     Flavoring
    -0.68
    ModLoader
    -0.67
     Contents
    -0.67
     chests
    -0.65
    achus
    -0.62
    natureconservancy
    -0.62
    uin
    -0.61
    POSITIVE LOGITS
    ruary
    0.87
    tein
    0.77
    cent
    0.71
     Scully
    0.65
     ANN
    0.63
    970
    0.61
    39
    0.61
    415
    0.61
    ann
    0.60
     McKenna
    0.59
    Activations Density 0.250%

    No Known Activations