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. 6-RES-JB
    6. 12571
    Prev
    Next
    INDEX
    Explanations

    ellipsis points (…) at the end of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    ellipsis or pauses in the text, indicating an ongoing thought or continuation

    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
     prosperity
    -0.74
     depletion
    -0.71
     cohesion
    -0.71
     oxide
    -0.71
     flourish
    -0.70
     prominence
    -0.69
     clashed
    -0.69
     misfortune
    -0.69
     antip
    -0.69
     rebell
    -0.68
    POSITIVE LOGITS
    BUT
    1.17
    until
    1.11
    except
    1.01
    among
    1.00
    yet
    1.00
    unless
    0.94
    but
    0.93
    why
    0.92
    they
    0.91
     âĢİ
    0.91
    Activations Density 0.048%

    No Known Activations