© 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. 0-RES-JB
    11. 22264
    Prev
    Next
    INDEX
    Explanations

    words related to confirmations or verifications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confirmation" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seless
    -0.69
    ishi
    -0.65
    oppers
    -0.62
    itect
    -0.62
     athlet
    -0.61
     illegally
    -0.60
     peacefully
    -0.60
    purpose
    -0.60
     collectively
    -0.59
    atra
    -0.58
    POSITIVE LOGITS
     confirmation
    4.06
     confirm
    2.21
    irmation
    2.08
     confirming
    2.06
    confirmed
    1.74
     verification
    1.72
     confirmed
    1.71
     validation
    1.60
     confirms
    1.55
     clarification
    1.48
    Activations Density 0.007%

    No Known Activations