© 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. 1-RES-JB
    11. 992
    Prev
    Next
    INDEX
    Explanations

    locations or places containing the word "view"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     notor
    -0.81
     abduct
    -0.76
     lull
    -0.75
     rhyth
    -0.74
     frantic
    -0.73
     digging
    -0.71
     economical
    -0.71
     biting
    -0.70
     repetitive
    -0.70
     deaf
    -0.70
    POSITIVE LOGITS
    view
    1.41
    views
    0.98
    edIn
    0.93
    finder
    0.89
    izable
    0.88
     View
    0.88
    port
    0.87
    eous
    0.87
    VIEW
    0.86
    ablishment
    0.82
    Activations Density 0.005%

    No Known Activations