© 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. 12769
    Prev
    Next
    INDEX
    Explanations

    phrases describing an underestimation or overestimation of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to estimation and exaggeration

    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
    ĪĴ
    -0.79
    ĸļ
    -0.77
    interrupted
    -0.74
    iston
    -0.68
    ulhu
    -0.64
    ģĸ
    -0.63
    vine
    -0.63
    bleacher
    -0.63
    opher
    -0.63
    mont
    -0.62
    POSITIVE LOGITS
     expectations
    0.98
    imate
    0.91
     importance
    0.90
     significance
    0.86
     magnitude
    0.84
     overest
    0.82
     how
    0.80
     exagger
    0.79
     severity
    0.78
     positives
    0.78
    Activations Density 0.113%

    No Known Activations