© 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. 10-RES-JB
    11. 11236
    Prev
    Next
    INDEX
    Explanations

    instances where there are criticisms or accusations of failure to act or respond appropriately

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating failures or shortcomings in actions or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anian
    -0.66
    moil
    -0.64
    avery
    -0.64
     obscurity
    -0.60
    unknown
    -0.59
    loo
    -0.59
     madness
    -0.59
    laughter
    -0.58
    den
    -0.58
    çĶ°
    -0.58
    POSITIVE LOGITS
     adequately
    1.60
     properly
    1.47
     adequate
    1.45
     sufficiently
    1.34
     sufficient
    1.33
     timely
    1.33
     enough
    1.32
     correctly
    1.30
    enough
    1.19
     Enough
    1.16
    Activations Density 0.672%

    No Known Activations