© 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. 12-RES-JB
    11. 3167
    Prev
    Next
    INDEX
    Explanations

    instances of negative or threatening language related to environmental issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating negative impacts or detrimental effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Giles
    -0.66
     Whedon
    -0.66
     narration
    -0.65
     bitters
    -0.65
     condu
    -0.64
     residue
    -0.64
     percept
    -0.63
     torches
    -0.62
     pencil
    -0.61
     omission
    -0.61
    POSITIVE LOGITS
    level
    1.40
    based
    1.36
    sized
    1.36
    specific
    1.33
    wide
    1.32
    mounted
    1.28
    scale
    1.26
    grown
    1.25
    building
    1.24
    size
    1.23
    Activations Density 0.071%

    No Known Activations