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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19290
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names that appear in multiple contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "appears" and related terms indicating frequency and presence in various contexts

    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
     dilig
    -0.70
    Progress
    -0.65
    acion
    -0.60
    ustom
    -0.60
    cise
    -0.59
    achine
    -0.58
     Winning
    -0.58
    ugu
    -0.57
    rug
    -0.56
    cig
    -0.56
    POSITIVE LOGITS
     prominently
    1.29
     elsewhere
    1.02
     mentioned
    1.01
     anywhere
    1.01
     appearing
    1.00
     therein
    0.97
     uttered
    0.96
    mentioned
    0.93
     referenced
    0.93
     reapp
    0.91
    Activations Density 0.496%

    No Known Activations