© 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. 1-RES-JB
    11. 16885
    Prev
    Next
    INDEX
    Explanations

    phrases indicating different stages or parts of a process

    oai_token-act-pair · gpt-3.5-turbo

    references to different stages or phases in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILLE
    -1.14
    riad
    -0.88
    Interstitial
    -0.83
    incinn
    -0.76
    Frameworks
    -0.73
    Honest
    -0.72
     glim
    -0.71
    intent
    -0.70
    åı
    -0.70
    nai
    -0.69
    POSITIVE LOGITS
     Phase
    1.27
     phase
    1.24
     phases
    1.16
    phase
    1.11
    Phase
    0.97
     stages
    0.83
     epoch
    0.78
     Genie
    0.78
    arthed
    0.76
     Centauri
    0.74
    Activations Density 0.008%

    No Known Activations