© 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. 6-RES-JB
    11. 12810
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with verbs in present tense

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate assertion or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.71
    hovah
    -0.58
     Photograph
    -0.55
    brance
    -0.55
     wearer
    -0.55
    ousands
    -0.54
    Exper
    -0.54
     pilgr
    -0.53
    immune
    -0.53
     civilisation
    -0.53
    POSITIVE LOGITS
     sarcast
    1.00
     rhet
    0.81
     apologizing
    0.75
    :]
    0.74
     emphatically
    0.73
     remarks
    0.72
     clar
    0.68
     bluntly
    0.68
    .):
    0.67
     apologized
    0.67
    Activations Density 0.824%

    No Known Activations