© 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. 18444
    Prev
    Next
    INDEX
    Explanations

    phrases related to completing or finishing tasks or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to completion or finishing tasks and responsibilities

    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
    soType
    -0.74
    Magikarp
    -0.68
    esis
    -0.67
     wielded
    -0.64
    tall
    -0.63
    elled
    -0.62
     Aware
    -0.62
    isSpecialOrderable
    -0.62
    osponsors
    -0.60
     Daly
    -0.59
    POSITIVE LOGITS
     semester
    0.85
    phies
    0.85
     cycle
    0.84
     sentence
    0.84
     sentences
    0.79
     exams
    0.79
     journey
    0.77
    earable
    0.75
     prepar
    0.75
     homework
    0.74
    Activations Density 0.171%

    No Known Activations