© 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. 7-RES-JB
    11. 3960
    Prev
    Next
    INDEX
    Explanations

    terms related to property ownership and personal relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to ownership or possessive relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guantanamo
    -0.78
    rossover
    -0.77
     analytic
    -0.72
     comparisons
    -0.71
     traject
    -0.71
     sleeper
    -0.70
    rawdownloadcloneembedreportprint
    -0.70
    scoring
    -0.66
     cryptography
    -0.65
     Guant
    -0.65
    POSITIVE LOGITS
     negligent
    0.88
    unia
    0.86
    estate
    0.83
     respons
    0.79
     frown
    0.79
     tenant
    0.78
     negligence
    0.74
     refuse
    0.74
     stern
    0.73
     forb
    0.70
    Activations Density 0.828%

    No Known Activations