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. 6-RES-JB
    6. 15962
    Prev
    Next
    INDEX
    Explanations

    numerical values or terms related to hitting high records

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to reaching or hitting specific metrics or levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onga
    -0.81
    atu
    -0.71
    croft
    -0.70
     endeav
    -0.67
     artic
    -0.65
    urat
    -0.64
    cell
    -0.64
    uristic
    -0.63
    fo
    -0.63
    rying
    -0.62
    POSITIVE LOGITS
    peak
    0.77
     midnight
    0.76
     peaks
    0.72
     Babel
    0.72
    ebin
    0.72
     puberty
    0.71
     coincide
    0.71
     climax
    0.70
     landfall
    0.69
     exhaustion
    0.68
    Activations Density 0.069%

    No Known Activations