© 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. 16336
    Prev
    Next
    INDEX
    Explanations

    the words "not" and "harvested"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express significant emotional or impactful 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
    ovo
    -0.61
    aptic
    -0.61
     Alternatively
    -0.54
    aren
    -0.53
    rehend
    -0.53
    éĥ
    -0.52
    usional
    -0.50
    neutral
    -0.50
    idity
    -0.50
    istani
    -0.50
    POSITIVE LOGITS
     alot
    1.83
     much
    1.67
     MUCH
    1.61
     many
    1.49
    much
    1.48
     lot
    1.41
     lots
    1.39
     everything
    1.38
     most
    1.37
     plenty
    1.31
    Activations Density 1.153%

    No Known Activations