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. 14130
    Prev
    Next
    INDEX
    Explanations

    verbs related to communication or actions

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to announcements, participation, and investigations

    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
    quart
    -0.76
    è¦ļéĨĴ
    -0.71
    assing
    -0.65
    Pic
    -0.65
     supposed
    -0.65
    pmwiki
    -0.65
    cas
    -0.64
    >>\
    -0.62
    Cas
    -0.61
    she
    -0.59
    POSITIVE LOGITS
     tomorrow
    0.81
    enance
    0.79
    ãĥį
    0.76
    ELY
    0.72
    vt
    0.70
    igate
    0.69
    ãĤ¿
    0.68
    ãĥ¼ãĥ
    0.66
    ezvous
    0.66
     anytime
    0.66
    Activations Density 0.431%

    No Known Activations