© 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. 10-RES-JB
    11. 20291
    Prev
    Next
    INDEX
    Explanations

    phrases that involve items or actions being displayed or used in conjunction with something else

    oai_token-act-pair · gpt-3.5-turbo

    the word "alongside" and related phrases indicating co-presentation or additional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jab
    -0.86
    pmwiki
    -0.78
    ahime
    -0.76
    enter
    -0.74
    asse
    -0.73
    eria
    -0.73
    xxx
    -0.73
    iltr
    -0.72
     encount
    -0.72
    bell
    -0.71
    POSITIVE LOGITS
     ours
    0.90
     hers
    0.89
     theirs
    0.84
     yours
    0.84
    lihood
    0.79
     them
    0.75
     others
    0.73
     other
    0.73
     him
    0.72
     fellow
    0.69
    Activations Density 0.051%

    No Known Activations