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. 3-RES-JB
    6. 19416
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate certainty or assurance

    oai_token-act-pair · gpt-3.5-turbo

    affirmative phrases indicating certainty or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.79
    Balt
    -0.71
    Vert
    -0.64
     Literature
    -0.63
    ULAR
    -0.62
    ivating
    -0.62
    arse
    -0.61
    ivated
    -0.61
    tumblr
    -0.60
    arser
    -0.60
    POSITIVE LOGITS
    tty
    0.64
     Monteneg
    0.62
     whoever
    0.62
    ounters
    0.62
     footing
    0.62
    eren
    0.61
     answer
    0.61
     someday
    0.60
    aido
    0.60
     impartial
    0.58
    Activations Density 0.314%

    No Known Activations