© 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. 10-RES-JB
    11. 8166
    Prev
    Next
    INDEX
    Explanations

    phrases related to consequences or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    verbs that suggest significant actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aries
    -0.60
     prone
    -0.58
    Correct
    -0.55
     tubing
    -0.54
    ans
    -0.53
     chart
    -0.53
     contrace
    -0.52
     caucuses
    -0.52
    cember
    -0.52
     nodd
    -0.52
    POSITIVE LOGITS
     the
    0.94
     its
    0.91
     their
    0.84
     his
    0.80
    the
    0.79
    his
    0.72
    their
    0.67
    assis
    0.66
     what
    0.65
     this
    0.64
    Activations Density 0.408%

    No Known Activations