© 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. 9677
    Prev
    Next
    INDEX
    Explanations

    specific commands for the audience to watch certain videos or read specific articles

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate recommended viewing or importance

    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
     nowhere
    -0.68
    abba
    -0.66
     intent
    -0.66
    ura
    -0.65
     recl
    -0.64
     Midlands
    -0.60
     wound
    -0.60
    ibel
    -0.60
     depressed
    -0.60
     bleeding
    -0.60
    POSITIVE LOGITS
     VIDEOS
    1.09
     WATCH
    0.93
    esome
    0.88
     Thumbnails
    0.86
    }}}
    0.81
     IMAGES
    0.80
    !]
    0.77
    WATCH
    0.77
    ARDS
    0.75
     WATCHED
    0.74
    Activations Density 0.008%

    No Known Activations