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. 4-RES-JB
    6. 18824
    Prev
    Next
    INDEX
    Explanations

    instances where an action is mentioned as continuing or persisting, despite other conditions or factors

    oai_token-act-pair · gpt-3.5-turbo

    the word "still" used in various contexts

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

    No Comments

    Negative Logits
    代
    -0.72
    insula
    -0.69
    ãĥ³ãĤ¸
    -0.67
    ocene
    -0.66
    Winter
    -0.64
     Salman
    -0.64
    velt
    -0.64
     Stim
    -0.63
    psey
    -0.63
    cture
    -0.63
    POSITIVE LOGITS
     technically
    0.96
     intact
    0.85
     retains
    0.85
     remains
    0.79
     remained
    0.76
     theoretically
    0.74
     manages
    0.71
     unanswered
    0.71
     remain
    0.70
     retaining
    0.70
    Activations Density 0.039%

    No Known Activations