© 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. 0-RES-JB
    11. 22215
    Prev
    Next
    INDEX
    Explanations

    mentions of organizing or organization-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organization and structural arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curses
    -0.71
     touchdown
    -0.70
     crossover
    -0.69
     baths
    -0.67
     glide
    -0.66
     straight
    -0.65
     slam
    -0.65
     bath
    -0.65
     nib
    -0.65
     Spray
    -0.64
    POSITIVE LOGITS
    organ
    4.44
    organized
    2.23
    Organ
    2.09
     Organ
    1.68
     organ
    1.46
     organise
    1.33
     organising
    1.27
     organised
    1.24
     organisation
    1.18
    organic
    1.17
    Activations Density 0.019%

    No Known Activations