© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10191
    Prev
    Next
    INDEX
    Explanations

    phrases related to concealment, solicitation, and controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disguise, identity concealment, and social issues

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

    No Comments

    Negative Logits
     Kaplan
    -0.65
     Weston
    -0.63
     Bellev
    -0.61
     ObamaCare
    -0.60
     Kern
    -0.59
     Ramos
    -0.58
     Eucl
    -0.56
     Williamson
    -0.56
     Sherman
    -0.56
     Aval
    -0.55
    POSITIVE LOGITS
    depending
    1.11
     thereof
    1.08
     alike
    0.90
     versa
    0.87
    abouts
    0.79
     depending
    0.79
    #$#$
    0.78
    Else
    0.71
    peat
    0.70
    nam
    0.69
    Activations Density 0.635%

    No Known Activations