© 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. 2719
    Prev
    Next
    INDEX
    Explanations

    phrases expressing beliefs, thoughts, and desires

    oai_token-act-pair · gpt-3.5-turbo

    expressions of belief or perception regarding knowledge and expectations

    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
     Paige
    -0.72
     Noir
    -0.70
    Mir
    -0.70
     Miranda
    -0.70
    pa
    -0.67
     235
    -0.67
    Pinterest
    -0.67
     æľ
    -0.67
     Pryor
    -0.66
    ranch
    -0.65
    POSITIVE LOGITS
    we
    0.92
    adi
    0.81
    WE
    0.80
     Twe
    0.80
    Twe
    0.79
    ^
    0.79
    df
    0.76
     Ulster
    0.75
     Weld
    0.75
     Webb
    0.74
    Activations Density 0.223%

    No Known Activations