© 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. 10060
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or lack thereof, particularly around waiting for responses or feedback

    oai_token-act-pair · gpt-3.5-turbo

    references to communication, particularly instances of not receiving responses

    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
    ortment
    -0.59
    omas
    -0.59
    LU
    -0.57
    ãĤ©
    -0.55
    ãĥ¼ãĥĨãĤ£
    -0.54
    avoid
    -0.54
    ãĤ¼ãĤ¦ãĤ¹
    -0.53
     Unknown
    -0.53
    ghan
    -0.52
    loo
    -0.52
    POSITIVE LOGITS
     anything
    1.40
     nor
    1.38
     anymore
    1.29
     anybody
    1.29
     anyone
    1.23
     any
    1.22
     slightest
    1.13
     anywhere
    1.07
    anything
    1.07
     ANY
    1.04
    Activations Density 0.336%

    No Known Activations