© 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. 6-RES-JB
    11. 2610
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by sentiments or actions

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of personal sentiment or experience

    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
    imum
    -0.69
    rift
    -0.68
    alky
    -0.65
    igmatic
    -0.63
    ruct
    -0.63
    utenberg
    -0.62
     Economic
    -0.61
    Street
    -0.60
    rontal
    -0.60
    Skip
    -0.60
    POSITIVE LOGITS
    'll
    1.21
    've
    1.09
     consequently
    1.04
     therefore
    0.97
    'm
    0.96
     shouldn
    0.96
     accordingly
    0.94
    'd
    0.92
     wondered
    0.91
     couldn
    0.90
    Activations Density 0.144%

    No Known Activations