Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 21894
    Prev
    Next
    INDEX
    Explanations

    indications of negation or refusal

    oai_token-act-pair · gpt-3.5-turbo

    negations or words indicating denial

    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
    Nice
    -0.70
    quickShipAvailable
    -0.69
     HUGE
    -0.64
     LOT
    -0.62
    GGGGGGGG
    -0.61
     lousy
    -0.61
     cleaner
    -0.60
     Seasons
    -0.60
    å¥
    -0.59
    emetery
    -0.59
    POSITIVE LOGITS
     necessarily
    1.22
     tolerate
    1.22
     hesitate
    1.22
    icably
    1.05
     be
    1.04
     allow
    1.02
    hin
    1.01
     relent
    0.98
     condone
    0.96
     interfere
    0.96
    Activations Density 0.090%

    No Known Activations