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. 12932
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disagreement or opposition

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding consumer choices and political stances on social issues

    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
    WAR
    -0.59
     Released
    -0.59
     RL
    -0.58
     NYC
    -0.55
    Born
    -0.53
     Weird
    -0.53
    agonists
    -0.53
    Pg
    -0.52
     Yor
    -0.52
     Whedon
    -0.52
    POSITIVE LOGITS
    )."
    1.29
    .")
    1.14
    .""
    1.13
    .'"
    1.11
    ."[
    1.01
    '."
    1.00
     â̦"
    0.99
    ."
    0.99
     ..."
    0.96
    }"
    0.96
    Activations Density 1.324%

    No Known Activations