© 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. 6175
    Prev
    Next
    INDEX
    Explanations

    numeric values preceded by the number 62

    oai_token-act-pair · gpt-3.5-turbo

    numeric values that are related to counts or measurements

    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
    ipe
    -0.69
     shack
    -0.66
     bund
    -0.63
     Mack
    -0.63
     association
    -0.63
     badass
    -0.61
    buff
    -0.61
     assistant
    -0.61
     Amar
    -0.61
    ipes
    -0.61
    POSITIVE LOGITS
    62
    2.57
    61
    2.36
    63
    2.24
    60
    2.09
    59
    1.79
    58
    1.66
     62
    1.60
    65
    1.57
     61
    1.57
    56
    1.47
    Activations Density 0.041%

    No Known Activations