© 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. 2-RES-JB
    11. 19588
    Prev
    Next
    INDEX
    Explanations

    names of universities, colleges, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names and terms related to individuals and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arro
    -0.92
    ives
    -0.86
    IVERS
    -0.80
    apego
    -0.78
    enge
    -0.75
    estern
    -0.75
    ulkan
    -0.75
    ivers
    -0.74
    ãģŁ
    -0.73
    itives
    -0.73
    POSITIVE LOGITS
    ŃĶ
    0.83
     orth
    0.77
     canopy
    0.75
     exting
    0.69
     crop
    0.69
     carriage
    0.68
    stairs
    0.66
     coffin
    0.65
     plates
    0.64
     lid
    0.64
    Activations Density 0.029%

    No Known Activations