© 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. 10-RES-JB
    11. 24416
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual observation or examination

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "look" and its variations

    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
    Fact
    -0.77
    accompan
    -0.71
     Trad
    -0.66
    ãĥĩãĤ£
    -0.66
    Repeat
    -0.65
     Recomm
    -0.65
    ICO
    -0.64
    CONCLUS
    -0.62
    kt
    -0.62
     Colleg
    -0.61
    POSITIVE LOGITS
     bored
    0.91
     puzzled
    0.88
     disgusted
    0.86
     ashamed
    0.85
     startled
    0.85
     curiously
    0.84
     astonished
    0.84
     embarrassed
    0.83
     pleased
    0.82
     sideways
    0.82
    Activations Density 0.060%

    No Known Activations