© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 11479
    Prev
    Next
    INDEX
    Explanations

    words related to taste and flavor

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tanginess or sourness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HAEL
    -0.68
    OCK
    -0.64
    âķIJâķIJ
    -0.63
     custody
    -0.62
    LEASE
    -0.61
    HCR
    -0.60
     inaction
    -0.59
    builders
    -0.58
     judging
    -0.58
    confidence
    -0.58
    POSITIVE LOGITS
    entially
    1.07
     tang
    1.06
    ential
    1.02
    eteenth
    0.89
    atra
    0.87
    bone
    0.85
    ophone
    0.81
    raph
    0.80
    ues
    0.79
    onga
    0.79
    Activations Density 0.006%

    No Known Activations