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. 7-RES-JB
    6. 12751
    Prev
    Next
    INDEX
    Explanations

    names of people along with specific actions or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures or movements

    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
    cknow
    -0.70
    ĪĴ
    -0.63
    é¾įå¥ij士
    -0.59
    ascript
    -0.58
    Wheel
    -0.58
     Pose
    -0.58
     Butcher
    -0.56
     blat
    -0.55
     asteroids
    -0.55
     PARK
    -0.53
    POSITIVE LOGITS
     squarely
    0.66
     prematurely
    0.65
     internationally
    0.63
     irresist
    0.63
     onto
    0.63
     considerably
    0.62
    into
    0.59
    ebted
    0.58
    wide
    0.58
     exponentially
    0.58
    Activations Density 0.772%

    No Known Activations