© 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. 7-RES-JB
    11. 23404
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial gain or unethical practices

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to exploitation and manipulation for economic gain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TPPStreamerBot
    -0.87
    recomm
    -0.82
    BuyableInstoreAndOnline
    -0.76
    ĪĴ
    -0.73
    spection
    -0.71
    Scot
    -0.70
    20439
    -0.69
    ometer
    -0.68
     Episcopal
    -0.68
    Reviewer
    -0.67
    POSITIVE LOGITS
     exploiting
    1.06
     deception
    1.03
     unsuspecting
    0.90
     exploit
    0.90
     disinformation
    0.87
     exploited
    0.86
     gull
    0.85
     deceive
    0.84
     extortion
    0.83
     domination
    0.82
    Activations Density 0.676%

    No Known Activations