© 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. 9295
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific brand or product named "Bitrix24"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific platform or service, particularly focused on Bitrix24

    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
    aptic
    -0.67
    ĻĤ
    -0.67
     critically
    -0.67
    stem
    -0.65
     sustaining
    -0.64
     persuasive
    -0.64
     sober
    -0.63
     sensible
    -0.63
     Enlightenment
    -0.62
    arers
    -0.61
    POSITIVE LOGITS
    andra
    1.07
    rix
    0.99
    ison
    0.94
    ius
    0.87
    eus
    0.85
    boxing
    0.82
    alus
    0.80
    naire
    0.79
    ipel
    0.77
    ieth
    0.76
    Activations Density 0.008%

    No Known Activations