© 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. 9-RES-JB
    11. 18070
    Prev
    Next
    INDEX
    Explanations

    adjectives with positive or negative connotations that are related to discussing about certain subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contrast or conjunctions in arguments

    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
     kinda
    -0.79
     alot
    -0.77
     whats
    -0.76
     americ
    -0.75
     doesnt
    -0.75
     didnt
    -0.73
     ok
    -0.73
     dont
    -0.70
     bye
    -0.66
    colour
    -0.65
    POSITIVE LOGITS
    ,
    0.86
    .,
    0.72
    ,.
    0.67
    irteen
    0.64
    SPONSORED
    0.64
    acket
    0.63
    %,
    0.60
    ohn
    0.59
    stakes
    0.59
    itia
    0.59
    Activations Density 0.354%

    No Known Activations