© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 9169
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or efforts

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating the existence or emergence of certain conditions or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ago
    -0.49
    stop
    -0.48
    )—
    -0.47
     pursu
    -0.45
    ugal
    -0.44
     pursuit
    -0.43
     Defeat
    -0.43
    catch
    -0.42
     Kro
    -0.42
     Catch
    -0.42
    POSITIVE LOGITS
    senal
    0.81
    rael
    0.69
    ©¶æ
    0.65
    ŃĶ
    0.62
    gins
    0.59
    20439
    0.59
     underway
    0.58
     etched
    0.57
     indeed
    0.57
     definitely
    0.57
    Activations Density 1.342%

    No Known Activations