Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2733
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "always" followed by an action or state

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to have" in various tenses

    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
     hither
    -0.65
     weave
    -0.63
     detail
    -0.62
     Steps
    -0.58
     mun
    -0.58
     KD
    -0.58
     Indie
    -0.57
     Turns
    -0.56
     undertaking
    -0.56
     Ki
    -0.55
    POSITIVE LOGITS
    enges
    0.79
    èª
    0.77
    å°Ĩ
    0.76
    ounters
    0.73
    ered
    0.73
    apter
    0.72
    anto
    0.72
    ORED
    0.71
    rences
    0.71
    alde
    0.71
    Activations Density 0.213%

    No Known Activations