© 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. 12697
    Prev
    Next
    INDEX
    Explanations

    phrases related to observations, perspectives, or viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "see" and its variations

    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
    esc
    -0.71
    lator
    -0.70
    cius
    -0.70
    late
    -0.69
    eware
    -0.67
    vag
    -0.65
     Researchers
    -0.65
    quer
    -0.64
    pour
    -0.60
    assisted
    -0.59
    POSITIVE LOGITS
     parallels
    1.29
     fit
    1.15
     similarities
    1.03
     possibilities
    0.88
     opportunity
    0.87
     eye
    0.86
     opportunities
    0.85
     visions
    0.85
     merit
    0.84
     positives
    0.81
    Activations Density 0.077%

    No Known Activations