© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12082
    Prev
    Next
    INDEX
    Explanations

    proper names with the letter "L" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prohibition
    -0.68
     pleasure
    -0.67
     Satanic
    -0.66
     prohibition
    -0.63
     actionGroup
    -0.62
     mitigating
    -0.62
     beware
    -0.62
     periodic
    -0.61
     Seeking
    -0.60
     boundaries
    -0.59
    POSITIVE LOGITS
    ibrarian
    1.29
    ifestyle
    1.29
    arkin
    1.27
    aptop
    1.21
    yrics
    1.20
    ocker
    1.18
    aund
    1.18
    acey
    1.16
    aughlin
    1.15
    ongevity
    1.13
    Activations Density 0.032%

    No Known Activations