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. 18220
    Prev
    Next
    INDEX
    Explanations

    phrases related to initiating or starting something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the initiation of new activities or entities

    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
     rooft
    -0.71
     props
    -0.69
     Constable
    -0.64
    enance
    -0.63
     guid
    -0.62
     Aval
    -0.62
     intercepted
    -0.58
     surfaces
    -0.57
     backdrop
    -0.57
     foresee
    -0.56
    POSITIVE LOGITS
     fray
    0.85
     anew
    0.82
     dialogue
    0.77
     countdown
    0.74
    uberty
    0.71
    enium
    0.69
     careers
    0.68
    wagen
    0.68
     journey
    0.67
     Pandora
    0.67
    Activations Density 0.165%

    No Known Activations