© 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. 3071
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    statements related to public accountability and political scrutiny

    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
    foreseen
    -0.66
    estones
    -0.64
    contact
    -0.63
     wearer
    -0.61
    CV
    -0.60
     Finder
    -0.59
     PW
    -0.59
    ãĥ´ãĤ¡
    -0.59
    ounter
    -0.58
    ãĥŁ
    -0.57
    POSITIVE LOGITS
     hypocrisy
    1.25
     arrogance
    1.15
     irresponsible
    1.10
     neglect
    1.08
     incompetence
    1.06
     hypocritical
    1.06
     ignorance
    1.03
     stupidity
    1.02
     misguided
    1.01
     ignorant
    1.01
    Activations Density 2.143%

    No Known Activations