© 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. 8-RES-JB
    11. 3014
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by possessive pronouns or nouns, indicating a change in ownership or possession

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or collective changes in beliefs or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.87
    APH
    -0.77
    ccoli
    -0.70
    cade
    -0.70
     Brach
    -0.67
     Barron
    -0.63
    PU
    -0.63
    gel
    -0.61
    eri
    -0.60
    Consumer
    -0.60
    POSITIVE LOGITS
     tack
    0.96
     tune
    0.88
     course
    0.87
     wording
    0.85
     diaper
    0.84
     diapers
    0.84
     minds
    0.81
     rules
    0.79
     allegiance
    0.79
     direction
    0.79
    Activations Density 0.147%

    No Known Activations