© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15677
    Prev
    Next
    INDEX
    Explanations

    the word "also" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "also."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AME
    -0.66
    UGE
    -0.66
    jam
    -0.62
     Sacramento
    -0.59
    IT
    -0.58
     Ascension
    -0.57
     Beng
    -0.56
     Tsukuyomi
    -0.56
    Age
    -0.56
    £
    -0.55
    POSITIVE LOGITS
     optionally
    0.81
     confir
    0.81
    xual
    0.80
     indirectly
    0.76
     includ
    0.76
     anecd
    0.73
    iffe
    0.72
     consider
    0.69
     include
    0.69
     briefly
    0.69
    Activations Density 0.063%

    No Known Activations