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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 3345
    Prev
    Next
    INDEX
    Explanations

    words related to impactful decisions or actions

    oai_token-act-pair · gpt-3.5-turbo

    words associated with decisive actions or moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mberg
    -0.84
    ©¶æ
    -0.84
    ramid
    -0.84
    rug
    -0.83
    hemy
    -0.79
    ryn
    -0.77
    guyen
    -0.77
    erve
    -0.76
    á
    -0.74
    opathy
    -0.73
    POSITIVE LOGITS
     decisive
    1.00
     defeat
    0.90
     victory
    0.89
     swing
    0.84
    éĹĺ
    0.84
     blow
    0.80
     reversal
    0.78
     showdown
    0.78
     victories
    0.76
     plunge
    0.76
    Activations Density 0.010%

    No Known Activations