© 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. 24144
    Prev
    Next
    INDEX
    Explanations

    the word "see" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of perception or viewpoint regarding situations

    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
     withd
    -0.66
    ÃŃa
    -0.64
    eware
    -0.64
    ium
    -0.63
     whistle
    -0.62
    cé
    -0.61
     anthem
    -0.61
     agric
    -0.59
     voyage
    -0.58
    Tweet
    -0.58
    POSITIVE LOGITS
     parallels
    0.95
    WARD
    0.84
    awed
    0.79
     similarities
    0.77
    ĸ
    0.76
    Ĺ
    0.73
     positives
    0.72
    ¿½
    0.71
    Ĭ±
    0.70
    poke
    0.69
    Activations Density 0.068%

    No Known Activations