Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19710
    Prev
    Next
    INDEX
    Explanations

    mention of "down" in the context of directional movement or positioning

    oai_token-act-pair · gpt-3.5-turbo

    references to "down" in a sports context, particularly related to football

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ön
    -0.72
    9999
    -0.67
    aceous
    -0.67
    Ann
    -0.66
    ature
    -0.65
    999
    -0.64
    ills
    -0.62
    / 
    -0.62
    mos
    -0.60
     Britons
    -0.60
    POSITIVE LOGITS
    graded
    1.06
    grading
    0.92
    stairs
    0.86
    played
    0.85
    grades
    0.81
    plays
    0.80
    river
    0.79
    onnaissance
    0.77
    swing
    0.74
    LOAD
    0.73
    Activations Density 0.034%

    No Known Activations