© 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. 8-RES-JB
    11. 16792
    Prev
    Next
    INDEX
    Explanations

    phrases indicating confusion or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases about reasons or explanations for something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esc
    -0.73
    ibaba
    -0.71
    mens
    -0.69
    ament
    -0.68
    ä¸Ĭ
    -0.66
    kees
    -0.65
     VIDEOS
    -0.65
    spect
    -0.65
    aquin
    -0.64
    iggins
    -0.64
    POSITIVE LOGITS
     somew
    1.09
     inexplicable
    0.94
    */(
    0.88
     unconsciously
    0.81
     forgot
    0.81
     unexplained
    0.80
     unlucky
    0.74
     incomprehensible
    0.73
     persists
    0.73
     resembling
    0.73
    Activations Density 0.046%

    No Known Activations