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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 22905
    Prev
    Next
    INDEX
    Explanations

    words related to evaluations or assessments

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "ess" or essential attributes of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Harbor
    -0.68
     baptized
    -0.66
    boarding
    -0.62
     è£ıè
    -0.58
     experienced
    -0.58
     Harbour
    -0.57
     charts
    -0.57
     ours
    -0.56
     zoo
    -0.56
     Chart
    -0.55
    POSITIVE LOGITS
    ess
    4.74
    esses
    3.58
    essing
    2.27
    ESS
    2.13
    essed
    2.08
    esse
    1.92
    essential
    1.32
    essions
    1.31
    essment
    1.26
    essa
    1.26
    Activations Density 0.026%

    No Known Activations