© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5238
    Prev
    Next
    INDEX
    Explanations

    numerical values related to amounts of money or measurements

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the number "25" in various contexts

    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
    ;;;;;;;;;;;;
    -0.73
     wom
    -0.69
     tact
    -0.64
     bang
    -0.63
     hon
    -0.62
     clos
    -0.61
     tack
    -0.58
     democracy
    -0.58
     omn
    -0.58
     thumbs
    -0.57
    POSITIVE LOGITS
    25
    3.16
    26
    2.24
    75
    2.22
    24
    2.15
    23
    2.12
    28
    2.11
    20
    2.09
    27
    2.09
    29
    2.08
    30
    2.07
    Activations Density 0.015%

    No Known Activations