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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 8421
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connecting phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditional statements and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avis
    -0.73
    manac
    -0.64
    bass
    -0.63
    inspired
    -0.60
    bow
    -0.58
    wow
    -0.58
    Synopsis
    -0.58
    punk
    -0.58
    bold
    -0.57
    ghazi
    -0.57
    POSITIVE LOGITS
    Depending
    0.93
     applicants
    0.91
     typically
    0.90
     offenders
    0.90
    ichever
    0.89
    Typically
    0.89
     recipients
    0.89
    typically
    0.88
     Depending
    0.86
    Alternatively
    0.86
    Activations Density 0.566%

    No Known Activations