© 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. 3957
    Prev
    Next
    INDEX
    Explanations

    words related to impeachment or other serious legal actions taken against individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to impeachment and unsanctioned actions

    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
     Danish
    -0.74
    heid
    -0.70
     Observer
    -0.69
    âĶģ
    -0.68
     Maid
    -0.68
     Dragonbound
    -0.67
     Warfare
    -0.64
     Manufacturer
    -0.64
     BDS
    -0.63
    etheless
    -0.62
    POSITIVE LOGITS
    lling
    1.10
    lete
    1.09
    ven
    1.01
    wn
    1.00
    aching
    0.98
    achers
    0.97
    eding
    0.94
    velop
    0.93
    vered
    0.93
    aving
    0.92
    Activations Density 0.021%

    No Known Activations