© 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. 6-RES-JB
    11. 9939
    Prev
    Next
    INDEX
    Explanations

    paragraphs with detailed descriptions and technical information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to analysis and inference processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.73
    `.
    -0.71
     Advertisement
    -0.68
    Medium
    -0.66
    %.
    -0.65
    $.
    -0.64
    thia
    -0.64
    >.
    -0.64
    }.
    -0.63
    ''.
    -0.63
    POSITIVE LOGITS
     politically
    0.55
     domestically
    0.54
     sequ
    0.53
     locally
    0.53
     physically
    0.52
     rehearsal
    0.52
     technically
    0.52
     exhaustive
    0.51
    oslav
    0.51
     constraints
    0.50
    Activations Density 1.945%

    No Known Activations