© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2915
    Prev
    Next
    INDEX
    Explanations

    references to males in informal settings, often characterized by a certain casual attitude or behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "dude" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SNP
    -0.82
     Labrador
    -0.76
    framework
    -0.75
     GST
    -0.74
    confidence
    -0.68
    ija
    -0.67
     Malt
    -0.65
    gow
    -0.65
     Strong
    -0.65
     Hilbert
    -0.65
    POSITIVE LOGITS
     dude
    1.60
     dudes
    1.50
     Spy
    1.32
    nec
    1.25
    Actor
    1.22
    obar
    1.21
    ulent
    1.07
    VICE
    1.00
     Shepard
    0.88
     spawned
    0.87
    Activations Density 0.065%

    No Known Activations