© 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. 3715
    Prev
    Next
    INDEX
    Explanations

    determiners followed by plural nouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of consensus or disagreement

    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
    soDeliveryDate
    -0.68
     instead
    -0.68
    staking
    -0.66
    éŃĶ
    -0.63
    ahime
    -0.62
    instead
    -0.61
     exting
    -0.60
     unden
    -0.58
     rather
    -0.58
     unfinished
    -0.57
    POSITIVE LOGITS
     ever
    1.39
     EVER
    1.25
     nor
    1.24
    ever
    1.13
     whatsoever
    1.12
     dared
    1.11
     necessarily
    1.10
     dare
    1.06
     bothered
    1.05
     survives
    1.04
    Activations Density 0.321%

    No Known Activations