© 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. 2-RES-JB
    11. 4493
    Prev
    Next
    INDEX
    Explanations

    words related to law enforcement officers

    oai_token-act-pair · gpt-3.5-turbo

    references to agents involved in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.94
    lihood
    -0.76
    PUT
    -0.71
    nings
    -0.70
    cept
    -0.69
    yss
    -0.68
    nz
    -0.68
    etooth
    -0.68
    FACE
    -0.65
    tty
    -0.64
    POSITIVE LOGITS
     agent
    1.24
     agents
    1.20
     Agent
    1.07
    agent
    1.04
    agents
    1.04
     Agents
    1.01
     prov
    0.93
    ilage
    0.89
    Agent
    0.84
    Sov
    0.83
    Activations Density 0.018%

    No Known Activations