© 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. 2508
    Prev
    Next
    INDEX
    Explanations

    political and social commentary

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors associated with people or groups

    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
    ãĥ´ãĤ¡
    -0.72
    ãĥĩãĤ£
    -0.72
    Enlarge
    -0.67
    ishable
    -0.67
     Ascension
    -0.67
    Mine
    -0.66
    VERTISEMENT
    -0.66
    FORMATION
    -0.66
    earch
    -0.65
    due
    -0.65
    POSITIVE LOGITS
     hypoc
    1.44
     arrog
    1.44
     willfully
    1.37
     blatantly
    1.35
     disregard
    1.27
     disreg
    1.26
     perpetuate
    1.25
     lied
    1.25
     falsely
    1.25
     refuse
    1.25
    Activations Density 0.413%

    No Known Activations