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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 5669
    Prev
    Next
    INDEX
    Explanations

    images or descriptions of clouds

    oai_token-act-pair · gpt-3.5-turbo

    mentions of clouds and skies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ischer
    -0.76
    GV
    -0.72
    uthor
    -0.67
    NUM
    -0.65
    otide
    -0.64
    NES
    -0.64
    inker
    -0.63
     Association
    -0.62
     Rehab
    -0.62
    endon
    -0.62
    POSITIVE LOGITS
     clouds
    3.93
     Clouds
    2.46
     cloud
    1.88
     skies
    1.76
    cloud
    1.75
     storms
    1.55
    storms
    1.45
     balloons
    1.44
    Cloud
    1.44
     cloudy
    1.33
    Activations Density 0.016%

    No Known Activations