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. 606
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to reacting or responding to something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "responding to"

    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
    wine
    -0.74
    ©¶æ¥µ
    -0.71
    Scope
    -0.71
    sky
    -0.71
    oval
    -0.69
    urn
    -0.69
    grand
    -0.68
    gebra
    -0.67
    rek
    -0.66
    lli
    -0.66
    POSITIVE LOGITS
    PsyNetMessage
    0.78
     behalf
    0.74
     denounce
    0.69
     counteract
    0.68
     affirm
    0.67
     criticism
    0.67
     defend
    0.66
     cue
    0.66
     reinforce
    0.65
     ARTICLE
    0.65
    Activations Density 0.084%

    No Known Activations