© 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. 20092
    Prev
    Next
    INDEX
    Explanations

    technical terms and codes/terms related to technology and software

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific agreements or contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     spawning
    -0.70
     inherit
    -0.66
    Die
    -0.66
    rd
    -0.66
     unintended
    -0.65
     Atkinson
    -0.62
    Conn
    -0.62
    Oak
    -0.62
     inheritance
    -0.60
    Il
    -0.59
    POSITIVE LOGITS
    ctory
    0.88
    mberg
    0.78
    onomy
    0.75
    minus
    0.74
    Ter
    0.73
     Terms
    0.73
    reement
    0.73
    orical
    0.71
    otional
    0.70
    terms
    0.70
    Activations Density 0.008%

    No Known Activations