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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 18260
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Verhagen" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'h' in various contexts

    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
     Clicker
    -0.80
    enhagen
    -0.79
    aution
    -0.79
    fman
    -0.74
     nomine
    -0.73
    ãĥ¯
    -0.73
     flush
    -0.73
     tremend
    -0.71
     mosqu
    -0.68
    psey
    -0.67
    POSITIVE LOGITS
    orses
    1.22
    awk
    1.17
    oused
    1.12
    ollow
    1.12
    ulk
    1.12
    wy
    1.07
    ometown
    1.06
    anging
    1.06
    ythm
    1.06
    undred
    1.05
    Activations Density 0.041%

    No Known Activations