© 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. 14857
    Prev
    Next
    INDEX
    Explanations

    the phrase "Needless to say" or similar expressions indicating an obvious statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a need to clarify or emphasize statements

    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
    pocket
    -0.64
    orno
    -0.64
    ortium
    -0.63
    oyer
    -0.61
    netflix
    -0.61
    nell
    -0.61
    wagon
    -0.60
    egal
    -0.60
    IDA
    -0.58
    glomer
    -0.58
    POSITIVE LOGITS
     Pwr
    0.62
    lege
    0.61
    quant
    0.59
    ¨
    0.59
    Quantity
    0.58
     note
    0.55
     Detected
    0.55
    itsu
    0.54
    oso
    0.54
    Increases
    0.54
    Activations Density 0.062%

    No Known Activations