© 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. 8515
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating ownership

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and their relations between entities

    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
     Photograph
    -0.71
    ourced
    -0.67
     Spend
    -0.63
    ieri
    -0.61
    }}}
    -0.61
    opsis
    -0.61
    tery
    -0.61
     Photographer
    -0.60
     compared
    -0.60
     Wouldn
    -0.60
    POSITIVE LOGITS
     own
    1.29
     knees
    1.15
     liking
    1.14
     detriment
    1.12
     fullest
    1.03
     respective
    1.03
    venge
    0.94
     superiors
    0.93
     ankles
    0.93
     mailbox
    0.92
    Activations Density 0.124%

    No Known Activations