© 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. 4299
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "no" in combination with qualifiers about the presence or absence of certain things or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express negation or the absence of something

    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
    endar
    -0.70
     flung
    -0.66
    adobe
    -0.63
     reborn
    -0.62
    ahime
    -0.62
    lass
    -0.62
     crowned
    -0.62
    ean
    -0.61
     bombed
    -0.61
     towed
    -0.61
    POSITIVE LOGITS
    xious
    0.96
    except
    0.91
     longer
    0.90
     doubt
    0.88
     whatsoever
    0.86
    oses
    0.85
     earthly
    0.81
     meaningful
    0.80
    THING
    0.79
     discern
    0.77
    Activations Density 0.075%

    No Known Activations