© 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. 9-RES-JB
    11. 15107
    Prev
    Next
    INDEX
    Explanations

    descriptions of illegal or unethical activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of scams and criminal activities involving manipulation or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.78
    ãĥ´
    -0.71
     reflection
    -0.70
     limitation
    -0.68
     Reflect
    -0.68
     Debate
    -0.68
    equal
    -0.67
    olon
    -0.67
    eatures
    -0.67
    utral
    -0.67
    POSITIVE LOGITS
     prostitutes
    1.29
     prostitute
    1.22
     pornographic
    1.21
     extortion
    1.20
     blackmail
    1.18
     smugg
    1.16
     prostitution
    1.15
     ransom
    1.14
     traffickers
    1.13
     bribes
    1.12
    Activations Density 0.975%

    No Known Activations