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. 8-RES-JB
    6. 2890
    Prev
    Next
    INDEX
    Explanations

    age-related statements or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to age and age-related details

    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
     subp
    -0.69
     Interstellar
    -0.67
     Tolkien
    -0.65
     simul
    -0.65
     ceremon
    -0.64
     modifiers
    -0.63
     ascend
    -0.62
     vibration
    -0.61
     warp
    -0.61
     heartbeat
    -0.61
    POSITIVE LOGITS
    girlfriend
    0.91
    rosse
    0.87
    nsics
    0.84
    old
    0.83
    ominium
    0.81
    young
    0.81
    inois
    0.81
    armed
    0.80
    police
    0.80
    essee
    0.79
    Activations Density 0.120%

    No Known Activations