© 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. 1-RES-JB
    11. 3095
    Prev
    Next
    INDEX
    Explanations

    masked or hidden entities or objects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disguises and large groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ©
    -1.00
    çīĪ
    -0.78
    éĸ
    -0.75
    ================================================================
    -0.69
     Dunham
    -0.67
    ritical
    -0.66
    ãĤ´ãĥ³
    -0.66
    issance
    -0.65
     Lama
    -0.64
    èĥ
    -0.63
    POSITIVE LOGITS
    cffffcc
    0.90
    Roaming
    0.81
    atility
    0.72
    punk
    0.71
    xual
    0.70
    stretched
    0.69
    rons
    0.68
    llor
    0.66
    naires
    0.66
    Voice
    0.66
    Activations Density 0.030%

    No Known Activations