© 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. 8-RES-JB
    11. 22547
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty, commonality, or ongoing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Doing
    -0.76
    ivating
    -0.68
    izont
    -0.67
    YING
    -0.67
     Writing
    -0.66
     Aware
    -0.66
     Saying
    -0.65
    onding
    -0.65
     Talking
    -0.64
    arter
    -0.64
    POSITIVE LOGITS
     resembled
    1.11
     existed
    1.11
     happened
    1.09
     resembles
    1.07
     coincides
    1.04
     happens
    1.04
     belonged
    1.04
     resided
    1.02
     derives
    1.01
     earns
    1.00
    Activations Density 0.225%

    No Known Activations