© 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. 10-RES-JB
    6. 21622
    Prev
    Next
    INDEX
    Explanations

    deadlines and time frames mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    deadlines and time frames related to events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     philos
    -0.68
    ram
    -0.66
     alike
    -0.65
     blurred
    -0.63
    nces
    -0.63
    illance
    -0.62
     detrim
    -0.62
    icult
    -0.60
     hepat
    -0.60
    ersive
    -0.60
    POSITIVE LOGITS
     submit
    0.94
     nominate
    0.91
     declare
    0.90
     decide
    0.90
     respond
    0.89
     reopen
    0.87
     submissions
    0.86
     formally
    0.85
     nominations
    0.85
     submitting
    0.85
    Activations Density 0.126%

    No Known Activations