© 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. 10-RES-JB
    11. 23426
    Prev
    Next
    INDEX
    Explanations

    phrases related to breaking news or current events

    oai_token-act-pair · gpt-3.5-turbo

    declarative statements or reported speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     util
    -1.02
     humour
    -0.97
     endeavour
    -0.93
     enqu
    -0.88
     wellbeing
    -0.87
     horrend
    -0.86
     whilst
    -0.84
     footballer
    -0.83
     mosqu
    -0.83
     realised
    -0.82
    POSITIVE LOGITS
     Officials
    1.37
     POLITICO
    1.25
     Critics
    1.21
     Among
    1.21
    WASHINGTON
    1.19
     Those
    1.19
    Newsletter
    1.16
    Obama
    1.14
    Republicans
    1.13
     UNCLASSIFIED
    1.13
    Activations Density 0.420%

    No Known Activations