© 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. 3574
    Prev
    Next
    INDEX
    Explanations

    phrases with emotional or emphatic expressions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" and variations of speech tone

    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
    issance
    -0.98
    etheless
    -0.78
    CLASSIFIED
    -0.74
    bryce
    -0.73
    hesda
    -0.71
    emis
    -0.68
    agos
    -0.68
    Published
    -0.68
    âĿ
    -0.65
    romeda
    -0.65
    POSITIVE LOGITS
     lieu
    1.23
     unison
    1.19
     terms
    1.00
    clus
    0.99
     tongues
    0.95
     Hindi
    0.95
     tones
    0.92
    appropriate
    0.92
    aud
    0.91
     vain
    0.91
    Activations Density 0.255%

    No Known Activations