© 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. 8-RES-JB
    11. 22552
    Prev
    Next
    INDEX
    Explanations

    mental states or emotional reactions expressed by people

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a large number of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILA
    -0.77
    odynamics
    -0.75
     Fury
    -0.74
     Eag
    -0.73
     Buster
    -0.71
     Chimera
    -0.68
     Spoon
    -0.68
    ahime
    -0.68
     Slime
    -0.67
     Advertisement
    -0.65
    POSITIVE LOGITS
     mistakenly
    0.96
     errone
    0.89
     overlooked
    0.86
     unwittingly
    0.79
     wrongly
    0.78
     wondering
    0.78
     misconceptions
    0.77
     mistaken
    0.76
     contemplate
    0.75
     alike
    0.75
    Activations Density 0.378%

    No Known Activations