© 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
    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. 23450
    Prev
    Next
    INDEX
    Explanations

    phrases related to situational causes and effects or logical relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate reasoning or rationale

    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
     awaited
    -0.80
     Rodham
    -0.64
    abled
    -0.62
    window
    -0.61
     Borough
    -0.59
     DISTRICT
    -0.58
     Booster
    -0.57
    Nut
    -0.57
    realDonaldTrump
    -0.57
    ':
    -0.56
    POSITIVE LOGITS
    Therefore
    0.85
    cknowled
    0.84
     analogy
    0.82
     therefore
    0.81
    tera
    0.77
    ichever
    0.77
     contrast
    0.73
     societies
    0.73
    inctions
    0.72
    entimes
    0.72
    Activations Density 0.477%

    No Known Activations