© 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. 6-RES-JB
    11. 3804
    Prev
    Next
    INDEX
    Explanations

    pronouns or other words indicating possession or association

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their associations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UFF
    -0.59
    UTC
    -0.59
     Penny
    -0.57
    Ŀ
    -0.57
    atory
    -0.57
     Hels
    -0.56
    ãĥ¼ãĥĨãĤ£
    -0.55
    antage
    -0.55
    extreme
    -0.54
    endish
    -0.54
    POSITIVE LOGITS
    'll
    0.98
     SHALL
    0.81
     MUST
    0.81
    'd
    0.81
     surely
    0.76
     must
    0.75
     certainly
    0.71
     SHOULD
    0.70
    CHA
    0.69
     shall
    0.67
    Activations Density 0.265%

    No Known Activations