© 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. 0-RES-JB
    11. 16631
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'points'

    oai_token-act-pair · gpt-3.5-turbo

    references to scoring or key metrics

    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
    ufact
    -0.74
    alias
    -0.71
    ntil
    -0.69
    ESE
    -0.67
    izoph
    -0.65
    pir
    -0.64
    omnia
    -0.64
    thel
    -0.63
    soDeliveryDate
    -0.63
    lict
    -0.59
    POSITIVE LOGITS
     points
    3.74
    points
    2.88
     Points
    2.58
    Points
    2.50
     point
    2.31
    point
    2.05
     pts
    1.87
    Point
    1.83
     Point
    1.77
     spots
    1.40
    Activations Density 0.016%

    No Known Activations