© 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. 10-RES-JB
    11. 8021
    Prev
    Next
    INDEX
    Explanations

    technical terms related to operations, plans, and involvement

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements about actions or circumstances

    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
    ãĥĩ
    -0.72
    à¨
    -0.65
     srfAttach
    -0.63
    null
    -0.62
    ãĥĺ
    -0.62
     Nirvana
    -0.62
    QB
    -0.59
    But
    -0.59
    Border
    -0.58
    æ°
    -0.58
    POSITIVE LOGITS
     nonetheless
    1.65
     nevertheless
    1.45
     certainly
    1.06
     anecd
    1.06
     suggestive
    0.90
     definitely
    0.86
     surely
    0.85
     occasionally
    0.84
     indirectly
    0.82
     sure
    0.80
    Activations Density 0.494%

    No Known Activations