© 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. 9-RES-JB
    11. 10051
    Prev
    Next
    INDEX
    Explanations

    negatively framed or critical comments

    oai_token-act-pair · gpt-3.5-turbo

    negative assessments of experiences or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GEAR
    -0.82
     Versus
    -0.76
     Reloaded
    -0.69
     File
    -0.67
     Rivals
    -0.66
     induction
    -0.66
     Downing
    -0.66
     Theft
    -0.66
     Pieces
    -0.66
     Caller
    -0.65
    POSITIVE LOGITS
    famous
    1.35
    existent
    1.32
    great
    1.25
    named
    1.22
    popular
    1.21
    educated
    1.20
    successful
    1.20
    powerful
    1.19
    biased
    1.19
    expensive
    1.18
    Activations Density 0.035%

    No Known Activations