© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 14454
    Prev
    Next
    INDEX
    Explanations

    phrases containing the expression "kind of"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey a sense of qualification or similarity

    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
    ared
    -0.78
    vale
    -0.71
    ovember
    -0.70
     Yard
    -0.70
    heid
    -0.69
    listed
    -0.67
    arie
    -0.66
    ajor
    -0.66
    DS
    -0.66
    brush
    -0.65
    POSITIVE LOGITS
     luck
    0.86
     weird
    0.75
     nonsense
    0.70
     things
    0.69
     relig
    0.65
     humility
    0.65
     stuff
    0.65
     incomprehensible
    0.64
     fun
    0.62
     thing
    0.62
    Activations Density 0.150%

    No Known Activations