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. 11344
    Prev
    Next
    INDEX
    Explanations

    phrases related to the beginning of a process or event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "initial" in various contexts

    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
    lov
    -0.80
    tto
    -0.75
    Sav
    -0.74
    rf
    -0.74
    cig
    -0.73
    masters
    -0.72
    hered
    -0.70
    yers
    -0.70
    gemony
    -0.68
    atu
    -0.68
    POSITIVE LOGITS
     stages
    1.02
     impressions
    0.94
     impression
    0.92
     responders
    0.90
     reaction
    0.90
    isations
    0.88
     assumption
    0.85
     batch
    0.85
    izations
    0.84
     phases
    0.83
    Activations Density 0.022%

    No Known Activations