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. 12444
    Prev
    Next
    INDEX
    Explanations

    researchers and institutions

    oai_token-act-pair · gpt-3.5-turbo

    instances of research affiliations or institutional references

    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
    ãĥĺ
    -0.77
    Quantity
    -0.75
    washer
    -0.73
    INGS
    -0.72
    ãĥĵ
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.68
    ãĢĤ
    -0.64
    ãĥĸ
    -0.64
    INS
    -0.63
     entit
    -0.63
    POSITIVE LOGITS
    sembly
    0.80
     alike
    0.71
     Colleges
    0.69
     allied
    0.66
     convened
    0.65
    hip
    0.64
    hran
    0.63
     POLITICO
    0.63
    vae
    0.63
    rak
    0.61
    Activations Density 0.293%

    No Known Activations