© 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. 3-RES-JB
    11. 10745
    Prev
    Next
    INDEX
    Explanations

    references to government ministries or departments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various government ministries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rounds
    -0.71
    bre
    -0.67
    avery
    -0.67
     Karma
    -0.67
     Pose
    -0.66
     Roses
    -0.64
    gers
    -0.64
    gets
    -0.63
     Card
    -0.62
     Seasons
    -0.61
    POSITIVE LOGITS
     ministry
    0.98
     ministries
    0.94
    idium
    0.89
    istry
    0.88
     Ministry
    0.81
     minister
    0.81
    etheless
    0.81
     apparatus
    0.81
    Office
    0.76
    artment
    0.76
    Activations Density 0.015%

    No Known Activations