© 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. 6806
    Prev
    Next
    INDEX
    Explanations

    people's titles and positions, especially those related to organizations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to directors and their affiliations

    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
    Joined
    -0.77
     Greeks
    -0.68
     Egyptians
    -0.67
    ador
    -0.63
    theless
    -0.63
    Tokens
    -0.62
     horr
    -0.62
    usercontent
    -0.61
     jurors
    -0.60
     chew
    -0.60
    POSITIVE LOGITS
     communications
    1.13
     Operations
    0.92
     Communications
    0.91
     Programs
    0.90
     Strategic
    0.89
     Photography
    0.88
     Programming
    0.84
     communication
    0.82
     Marketing
    0.82
    orney
    0.81
    Activations Density 0.064%

    No Known Activations