© 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. 4-RES-JB
    11. 7702
    Prev
    Next
    INDEX
    Explanations

    the name "Nik" followed by different suffixes or prefixes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of names, particularly the name "Nik" in various contexts

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

    No Comments

    Negative Logits
    LOAD
    -0.87
    GROUND
    -0.82
    heads
    -0.74
     Cellular
    -0.71
    HAHAHAHA
    -0.70
    head
    -0.70
    BACK
    -0.67
     SPORTS
    -0.66
    reaching
    -0.65
    dress
    -0.65
    POSITIVE LOGITS
    aido
    1.24
    opol
    1.09
    olas
    1.08
    eties
    1.07
    ola
    1.03
    orius
    1.00
    umar
    1.00
    elsen
    0.99
    ita
    0.98
    onite
    0.97
    Activations Density 0.009%

    No Known Activations