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. 11-RES-JB
    6. 15442
    Prev
    Next
    INDEX
    Explanations

    expressions related to opinions or feelings

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal responsibility or actions taken by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idding
    -0.79
    tree
    -0.79
    naire
    -0.74
    dropping
    -0.74
    arie
    -0.73
    band
    -0.71
     Machina
    -0.70
    ansas
    -0.70
    arter
    -0.68
    mingham
    -0.68
    POSITIVE LOGITS
     pains
    1.27
     pride
    1.25
     offence
    1.14
     pleasure
    1.11
     cues
    1.09
     precedence
    1.09
     offense
    1.08
     advantage
    1.07
     comfort
    1.05
     responsibility
    1.05
    Activations Density 0.082%

    No Known Activations