© 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. 6-RES-JB
    11. 1677
    Prev
    Next
    INDEX
    Explanations

    declarative statements preceding with "the truth is" or similar phrases

    oai_token-act-pair · gpt-3.5-turbo

    statements emphasizing truth or factual assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -0.92
    yip
    -0.76
    robe
    -0.76
    mods
    -0.73
    reciation
    -0.69
    oslav
    -0.67
    ONSORED
    -0.66
    pload
    -0.65
    Interstitial
    -0.65
     fever
    -0.64
    POSITIVE LOGITS
    ACTED
    0.71
     Roe
    0.71
    etheless
    0.69
    matter
    0.68
     matter
    0.65
    çİĭ
    0.65
     Franken
    0.64
     Lange
    0.64
     relevance
    0.62
     reality
    0.62
    Activations Density 0.149%

    No Known Activations