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. 23345
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    names and associated titles or roles of individuals

    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
     stale
    -0.50
    ',"
    -0.50
     reliant
    -0.48
     deterrent
    -0.46
    ?'"
    -0.46
    ,'"
    -0.46
     vulnerability
    -0.45
    ?".
    -0.45
    ,'
    -0.44
     corros
    -0.44
    POSITIVE LOGITS
    çͰ
    0.60
    ospons
    0.60
    itled
    0.54
    ãĥĬ
    0.54
    çļ
    0.52
    itone
    0.52
    anky
    0.51
    anan
    0.51
    å·
    0.48
    aug
    0.48
    Activations Density 2.528%

    No Known Activations