© 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. 7-RES-JB
    11. 22615
    Prev
    Next
    INDEX
    Explanations

    sentences where the speaker is expressing uncertainty or contemplation

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing personal opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    472
    -0.72
    ña
    -0.72
    pora
    -0.69
    415
    -0.67
    PROV
    -0.66
    ãģ®æ
    -0.64
    aro
    -0.63
    473
    -0.63
    481
    -0.61
    448
    -0.61
    POSITIVE LOGITS
     nonetheless
    1.51
     nevertheless
    1.35
     darn
    1.13
    etheless
    1.06
     damn
    1.03
     definitely
    0.93
     suffice
    0.92
     proble
    0.91
     ain
    0.87
     awfully
    0.85
    Activations Density 0.414%

    No Known Activations