© 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. 8-RES-JB
    11. 3042
    Prev
    Next
    INDEX
    Explanations

    phrases related to excitement and progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating collective experiences and shared accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enlarge
    -0.82
    SPONSORED
    -0.73
    toggle
    -0.73
    interstitial
    -0.70
    bury
    -0.68
    atal
    -0.67
    âĵĺ
    -0.65
    bush
    -0.64
    Fake
    -0.63
    rule
    -0.62
    POSITIVE LOGITS
     certainly
    1.08
     definitely
    1.06
     also
    1.02
     currently
    0.98
     already
    0.94
     hoping
    0.94
     meanwhile
    0.92
     furthermore
    0.89
     thrilled
    0.89
     therefore
    0.88
    Activations Density 0.578%

    No Known Activations