© 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. 773
    Prev
    Next
    INDEX
    Explanations

    introductory phrases that are common in written text, such as "sent a campus-wide email" and "The LAPD released a statement."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain commas, indicating a possible list or detailed explanations

    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
    izen
    -0.75
    rup
    -0.74
    cius
    -0.71
    ertain
    -0.71
    aimon
    -0.70
    ry
    -0.67
    texture
    -0.66
     tower
    -0.65
    ome
    -0.65
    mos
    -0.65
    POSITIVE LOGITS
     confirming
    1.07
     indicating
    1.07
     citing
    1.05
     namely
    1.05
     noting
    1.04
     stating
    1.02
     outlining
    1.02
     titled
    0.98
     albeit
    0.96
     which
    0.96
    Activations Density 0.370%

    No Known Activations