© 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. 11-RES-JB
    11. 17729
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant points or key moments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant changes or points of transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.81
    exempt
    -0.69
    rely
    -0.68
    itism
    -0.67
    croft
    -0.66
    soever
    -0.65
    reci
    -0.65
    omnia
    -0.65
    zech
    -0.65
    cffff
    -0.64
    POSITIVE LOGITS
     point
    2.03
     points
    1.58
    point
    1.50
     Point
    1.48
    Point
    1.37
    points
    1.27
     Points
    1.20
    Points
    1.19
     stage
    1.00
     spot
    0.95
    Activations Density 0.200%

    No Known Activations