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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 17334
    Prev
    Next
    INDEX
    Explanations

    instances where the speaker expresses a subjective opinion or emphasizes a point

    oai_token-act-pair · gpt-3.5-turbo

    instances of conversational interjections or filler phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.78
    stad
    -0.77
    ा
    -0.69
    yx
    -0.69
    mage
    -0.67
    MpServer
    -0.67
    UGC
    -0.67
    MRI
    -0.66
    SourceFile
    -0.66
     Result
    -0.65
    POSITIVE LOGITS
     yeah
    1.10
     honestly
    0.89
     imagine
    0.87
     uh
    0.85
     wow
    0.82
     maybe
    0.78
     technically
    0.78
     hey
    0.77
     obviously
    0.76
     Honestly
    0.74
    Activations Density 0.040%

    No Known Activations