Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20469
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions that involve physical manipulation or movement

    oai_token-act-pair · gpt-3.5-turbo

    word segments and suffixes related to diminutive or trivializing forms

    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
    ioch
    -0.80
    Downloadha
    -0.79
    govtrack
    -0.78
    ĪĴ
    -0.78
    omes
    -0.72
    hemy
    -0.72
    uries
    -0.69
    vernment
    -0.68
    ß
    -0.67
     Extrem
    -0.67
    POSITIVE LOGITS
    tle
    1.36
    butt
    1.23
    mont
    0.95
    fish
    0.93
    estones
    0.88
    ty
    0.87
    bum
    0.86
    brate
    0.85
    pole
    0.85
    brates
    0.85
    Activations Density 0.012%

    No Known Activations