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. 0-RES-JB
    6. 5448
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Detective"

    oai_token-act-pair · gpt-3.5-turbo

    the word "detective" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     margin
    -0.83
     races
    -0.77
     reins
    -0.77
     margins
    -0.71
     collegiate
    -0.70
     qualifiers
    -0.70
     holiest
    -0.68
     parentheses
    -0.68
     capital
    -0.68
     grace
    -0.67
    POSITIVE LOGITS
    Det
    3.67
    det
    3.17
     Det
    2.53
     Detect
    2.02
    Detect
    2.02
     Detective
    1.74
     DET
    1.68
     Detection
    1.50
     detector
    1.49
    detail
    1.39
    Activations Density 0.021%

    No Known Activations