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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 14307
    Prev
    Next
    INDEX
    Explanations

    phrases related to objects or people experiencing a sudden or significant decrease or loss

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to falling or dropping off

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesday
    -0.89
    merce
    -0.76
    ãĥ£
    -0.73
    uterte
    -0.73
    gp
    -0.70
    oteric
    -0.69
    ilateral
    -0.69
    gew
    -0.68
    Ô
    -0.67
    reetings
    -0.66
    POSITIVE LOGITS
     cliffs
    0.97
     cliff
    0.85
     curve
    0.79
     bushes
    0.77
     stairs
    0.76
     ceilings
    0.76
     trees
    0.76
     roofs
    0.75
     nowhere
    0.74
     Curve
    0.73
    Activations Density 0.076%

    No Known Activations