© 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. 9145
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific policies or strategies

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or constructs that involve the word "of," particularly in a policy context

    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
    emonium
    -0.71
    rafted
    -0.68
    enges
    -0.67
    ETS
    -0.67
    eways
    -0.66
    oor
    -0.66
    conom
    -0.66
    aces
    -0.65
    UA
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    POSITIVE LOGITS
     ignoring
    1.14
     avoiding
    1.12
     preferring
    1.11
     letting
    1.11
     excluding
    1.08
     relying
    1.07
     keeping
    1.07
     favoring
    1.06
     selecting
    1.06
     refusing
    1.04
    Activations Density 0.176%

    No Known Activations