© 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. 3-RES-JB
    11. 12233
    Prev
    Next
    INDEX
    Explanations

    words related to scientific and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    topics related to environmental conditions and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }}}
    -0.59
     Student
    -0.53
    claw
    -0.53
    ĸļ
    -0.52
    :]
    -0.52
    stellar
    -0.51
    },"
    -0.50
    ydia
    -0.50
    avering
    -0.48
    answered
    -0.48
    POSITIVE LOGITS
    glers
    0.54
    grain
    0.53
     oxid
    0.48
    Pref
    0.48
     substr
    0.47
     powder
    0.46
     goats
    0.45
    sels
    0.45
     cows
    0.45
     grown
    0.45
    Activations Density 2.801%

    No Known Activations