© 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. 11-RES-JB
    11. 16327
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs indicating personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of forced affection or obligation in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢij
    -0.88
    —
    -0.83
    Enlarge
    -0.80
     ÂŃ
    -0.77
    ––
    -0.75
    ä¹ĭ
    -0.73
    –
    -0.71
    ®,
    -0.69
     Stephens
    -0.69
    ogue
    -0.68
    POSITIVE LOGITS
     dont
    1.75
     didnt
    1.71
     doesnt
    1.57
     wont
    1.38
     cant
    1.30
    nt
    1.14
     wanna
    1.12
     defin
    1.04
     dunno
    0.99
     alot
    0.98
    Activations Density 0.460%

    No Known Activations