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. 7-RES-JB
    6. 2407
    Prev
    Next
    INDEX
    Explanations

    phrases relating to effects or consequences

    oai_token-act-pair · gpt-3.5-turbo
    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
    bow
    -0.76
    cele
    -0.69
    approved
    -0.64
    course
    -0.61
    mad
    -0.60
    away
    -0.60
    fter
    -0.59
    ption
    -0.58
    ilings
    -0.58
    media
    -0.58
    POSITIVE LOGITS
     tremend
    0.84
     alot
    0.79
     raining
    0.78
    bnb
    0.77
    ynthesis
    0.71
     CTR
    0.70
    ometimes
    0.69
    rontal
    0.67
    ichick
    0.63
    inently
    0.63
    Activations Density 0.241%

    No Known Activations