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. 14484
    Prev
    Next
    INDEX
    Explanations

    commands or coding-related keywords

    oai_token-act-pair · gpt-3.5-turbo

    elements related to scripting, coding, or metadata

    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
    emis
    -0.74
    untled
    -0.73
    autical
    -0.70
    isks
    -0.68
    lag
    -0.67
    istical
    -0.66
    cade
    -0.66
    chid
    -0.66
    urances
    -0.65
    ento
    -0.65
    POSITIVE LOGITS
    ©¶æ
    0.91
     alias
    0.81
    =""
    0.74
     Uri
    0.73
     Delete
    0.70
     Replace
    0.67
     pref
    0.65
     dun
    0.64
     tc
    0.64
     aliases
    0.63
    Activations Density 0.311%

    No Known Activations