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. 7-RES-JB
    6. 506
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases with endings that imply continuation or additional content

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rall
    -0.68
     conservatism
    -0.68
     advis
    -0.67
     flagged
    -0.67
     quir
    -0.65
     antip
    -0.64
    omore
    -0.63
     informed
    -0.63
     estab
    -0.63
     masc
    -0.63
    POSITIVE LOGITS
     Therefore
    1.15
     Secondly
    1.14
     Conversely
    1.12
     Basically
    1.11
     Needless
    1.10
     Obviously
    1.10
     Wouldn
    1.09
     Likewise
    1.09
     Similarly
    1.08
     Examples
    1.06
    Activations Density 0.683%

    No Known Activations