© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 295
    Prev
    Next
    INDEX
    Explanations

    names of locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical locations and proper names

    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
     parity
    -0.67
     tremend
    -0.64
    forces
    -0.58
    sworth
    -0.55
     Enix
    -0.55
    risome
    -0.54
    ãĤŃ
    -0.54
    ription
    -0.54
    JUST
    -0.53
    sing
    -0.53
    POSITIVE LOGITS
    endi
    0.64
     Returns
    0.59
     Gadget
    0.55
     apologised
    0.55
     heals
    0.55
    ;;;;;;;;;;;;
    0.55
    theless
    0.55
    loo
    0.54
    aways
    0.53
     remembers
    0.53
    Activations Density 0.688%

    No Known Activations