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. 4997
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific point in time or level of completion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate reference to time or progression

    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
    Pakistan
    -0.71
    acea
    -0.70
    dylib
    -0.62
    ãĥĺ
    -0.60
     Malcolm
    -0.60
    zai
    -0.59
    vic
    -0.57
    aiden
    -0.55
     Messenger
    -0.55
     è£ıè¦ļéĨĴ
    -0.55
    POSITIVE LOGITS
    ħĭ
    0.75
     bounds
    0.74
     scrutiny
    0.70
    phrine
    0.70
     levels
    0.69
    dden
    0.68
    dfx
    0.67
    utenberg
    0.66
    displayText
    0.66
    pload
    0.64
    Activations Density 0.152%

    No Known Activations