© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4863
    Prev
    Next
    INDEX
    Explanations

    verbs related to expressing disapproval or negative opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of criticism directed toward individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTE
    -0.77
    ther
    -0.73
    ammy
    -0.72
    ëĭ
    -0.71
    rh
    -0.68
    minster
    -0.67
    abouts
    -0.66
    bourne
    -0.65
    MG
    -0.65
    alde
    -0.65
    POSITIVE LOGITS
     hypocrisy
    0.72
     Sark
    0.67
     merciless
    0.66
     harshly
    0.66
     remarks
    0.65
     comments
    0.65
     commenters
    0.65
     homosexuals
    0.63
     Jaw
    0.63
     hypoc
    0.63
    Activations Density 0.099%

    No Known Activations