© 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. 10-RES-JB
    11. 2811
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consolidation or gathering of information into a single location or entity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to consolidation or gathering information in a single entity or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    friends
    -0.84
    ãĥ©ãĥ³
    -0.81
    osponsors
    -0.79
    emies
    -0.78
    anwhile
    -0.78
    apons
    -0.78
    wives
    -0.75
    erved
    -0.74
    iddles
    -0.72
    ends
    -0.72
    POSITIVE LOGITS
     cohesive
    1.20
     unified
    1.06
     coherent
    1.02
     person
    0.99
     entity
    0.98
     seamless
    0.97
     package
    0.97
     single
    0.96
     organism
    0.94
     piece
    0.94
    Activations Density 0.123%

    No Known Activations