© 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. 9-RES-JB
    11. 4786
    Prev
    Next
    INDEX
    Explanations

    differences or variations in a given context

    oai_token-act-pair · gpt-3.5-turbo

    the word "different" and its various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HP
    -0.66
    OIL
    -0.64
     Beans
    -0.64
    DEV
    -0.58
    Notes
    -0.57
    WF
    -0.56
    emp
    -0.56
    Chance
    -0.55
     roundup
    -0.55
    ©¶æ
    -0.54
    POSITIVE LOGITS
    iating
    1.86
    iates
    1.62
    iator
    1.41
    iated
    1.33
    ials
    1.30
    iations
    1.20
    iable
    1.13
     than
    1.09
    iate
    1.08
    ially
    1.07
    Activations Density 0.048%

    No Known Activations