© 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. 6-RES-JB
    11. 11665
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or topics that are unrelated or unconnected

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of relation or relevance between concepts

    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
    hap
    -0.75
    hai
    -0.73
    soon
    -0.72
    DragonMagazine
    -0.71
    Fig
    -0.70
    Sometimes
    -0.67
    é¾įåĸļ士
    -0.66
    sometimes
    -0.65
    soDeliveryDate
    -0.65
    raq
    -0.65
    POSITIVE LOGITS
     anymore
    1.44
     nor
    1.26
     anything
    1.22
     any
    1.22
     whatsoever
    1.20
     necessarily
    1.07
     anybody
    1.06
     slightest
    1.01
     anyone
    0.99
     ANY
    0.96
    Activations Density 0.330%

    No Known Activations