© 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. 0-RES-JB
    6. 22291
    Prev
    Next
    INDEX
    Explanations

    queries or requests starting with "Can" and followed by a specific action or question

    oai_token-act-pair · gpt-3.5-turbo

    requests or inquiries that start with the word "Can."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sob
    -0.65
    uria
    -0.61
     fugitive
    -0.61
     Frey
    -0.61
     throat
    -0.60
     residue
    -0.60
     rogue
    -0.59
     hours
    -0.59
     adjud
    -0.58
     heroin
    -0.57
    POSITIVE LOGITS
    Can
    3.51
    CAN
    2.19
     Can
    2.07
    can
    2.00
    Could
    1.70
    Does
    1.64
    Has
    1.62
    Is
    1.53
    Are
    1.48
     CAN
    1.41
    Activations Density 0.015%

    No Known Activations