© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10009
    Prev
    Next
    INDEX
    Explanations

    phrases containing "and/or" connectors

    oai_token-act-pair · gpt-3.5-turbo

    instances of slashes or separators commonly used in lists or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scrib
    -0.79
     Targ
    -0.68
     guid
    -0.65
     pans
    -0.63
     aspir
    -0.61
     Shooter
    -0.61
     shuffle
    -0.60
     millionaires
    -0.60
     liner
    -0.60
     tabl
    -0.59
    POSITIVE LOGITS
    or
    1.27
    possibly
    1.10
    probably
    1.06
    especially
    1.06
    course
    1.00
    perhaps
    0.99
    mostly
    0.99
    maybe
    0.98
    OR
    0.97
    usually
    0.96
    Activations Density 0.019%

    No Known Activations