© 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. 2700
    Prev
    Next
    INDEX
    Explanations

    the term "Moody" along with words related to predictions or forecasts

    oai_token-act-pair · gpt-3.5-turbo

    references to credit ratings and economic outlooks

    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
    Interstitial
    -0.99
    Anth
    -0.80
    Machine
    -0.79
    adding
    -0.77
    hall
    -0.77
    assault
    -0.77
    ique
    -0.75
    ICLE
    -0.73
    rose
    -0.73
    Upload
    -0.73
    POSITIVE LOGITS
     outlook
    0.86
     eagle
    0.81
     Moody
    0.77
    idth
    0.75
     downgrade
    0.75
    vantage
    0.68
     daylight
    0.67
     Outlook
    0.67
     rating
    0.65
     eyed
    0.64
    Activations Density 0.078%

    No Known Activations