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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 11940
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and commands

    oai_token-act-pair · gpt-3.5-turbo

    options and settings related to file handling and system configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    axies
    -0.82
    tumblr
    -0.71
    united
    -0.68
    ymph
    -0.67
    cade
    -0.67
    atur
    -0.65
    odcast
    -0.65
    guns
    -0.64
     drawings
    -0.64
    roach
    -0.63
    POSITIVE LOGITS
     defaults
    1.35
     default
    1.23
     override
    1.15
     prefix
    1.14
     overr
    1.14
     parameter
    1.13
     Default
    1.13
     Enabled
    1.10
     timeout
    1.07
     Ignore
    1.07
    Activations Density 0.336%

    No Known Activations