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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10293
    Prev
    Next
    INDEX
    Explanations

    screen sizes in inches

    oai_token-act-pair · gpt-3.5-turbo

    mentions of screen sizes in inches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sterdam
    -0.85
    ¥µ
    -0.79
    gaard
    -0.79
    Kings
    -0.77
    erg
    -0.76
    eln
    -0.74
    brates
    -0.74
    ggies
    -0.74
    brate
    -0.74
    anwhile
    -0.73
    POSITIVE LOGITS
    cliffe
    0.74
    inch
    0.72
    pin
    0.71
     floppy
    0.71
     TVs
    0.69
     prick
    0.68
    icago
    0.67
    combe
    0.67
    apixel
    0.67
     nails
    0.66
    Activations Density 0.013%

    No Known Activations