© 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. 18759
    Prev
    Next
    INDEX
    Explanations

    requests or expressions of interest

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing desire or conditional statements

    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
    è¦ļéĨĴ
    -0.64
     Brill
    -0.63
     Claus
    -0.58
     Kiw
    -0.57
     juven
    -0.56
     Chal
    -0.56
    RAM
    -0.55
     Jarrett
    -0.54
    bound
    -0.54
     Timber
    -0.54
    POSITIVE LOGITS
     prefer
    1.47
    rather
    1.20
     rather
    1.19
     gladly
    1.16
     dearly
    1.15
     like
    1.10
     love
    1.04
     LOVE
    1.00
     appreciate
    0.98
     ideally
    0.96
    Activations Density 0.167%

    No Known Activations