Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20239
    Prev
    Next
    INDEX
    Explanations

    words related to criticism and negative evaluation of specific individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to criticism or negative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    abouts
    -0.78
    ãĥĦ
    -0.73
    lycer
    -0.72
     sidx
    -0.72
    pole
    -0.71
    ãĥ¯ãĥ³
    -0.70
    agos
    -0.69
    Ranked
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.66
    emetery
    -0.66
    POSITIVE LOGITS
     critics
    0.91
     liberals
    0.84
     President
    0.82
     environmentalists
    0.82
     hypocrisy
    0.82
     politicians
    0.81
     inaction
    0.81
     Republicans
    0.80
     Gov
    0.80
     lawmakers
    0.78
    Activations Density 0.144%

    No Known Activations