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. 5-RES-JB
    6. 11849
    Prev
    Next
    INDEX
    Explanations

    instances of phrases related to trying or experimenting with something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "try out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cious
    -0.69
    antry
    -0.68
    aving
    -0.67
    VA
    -0.66
     fabrication
    -0.64
    Ret
    -0.61
    eries
    -0.61
    ``
    -0.60
    ellery
    -0.58
    ave
    -0.58
    POSITIVE LOGITS
    fitted
    0.75
    stretched
    0.71
    doors
    0.69
    grown
    0.69
    smart
    0.67
    lived
    0.66
    flows
    0.63
    izabeth
    0.62
     Eck
    0.62
    ources
    0.61
    Activations Density 0.036%

    No Known Activations