© 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. 0-RES-JB
    11. 20248
    Prev
    Next
    INDEX
    Explanations

    keywords related to straightforwardness and clarity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "obvious."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    halla
    -0.70
    ®
    -0.67
    Serv
    -0.65
    lie
    -0.63
     Profile
    -0.62
    roth
    -0.60
    ourses
    -0.60
    lio
    -0.59
    gr
    -0.59
    Â
    -0.59
    POSITIVE LOGITS
     obvious
    3.44
     apparent
    1.93
     evident
    1.75
     glaring
    1.62
     blatant
    1.54
     undeniable
    1.49
     understandable
    1.40
     noticeable
    1.38
     clear
    1.37
     conspicuous
    1.31
    Activations Density 0.016%

    No Known Activations