Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2371
    Prev
    Next
    INDEX
    Explanations

    questions or prompts querying for memories or recalling specific events or situations

    oai_token-act-pair · gpt-3.5-turbo

    the word "remember" and related concepts of recalling past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qus
    -0.77
    inery
    -0.75
    orthy
    -0.74
    tain
    -0.74
    izons
    -0.72
    igible
    -0.72
    ople
    -0.71
    estyles
    -0.70
    lems
    -0.70
    hest
    -0.69
    POSITIVE LOGITS
     memories
    0.98
     vividly
    0.91
     childhood
    0.86
     nostalg
    0.86
     fond
    0.84
     memorable
    0.84
     memory
    0.76
     earliest
    0.74
     history
    0.74
     days
    0.74
    Activations Density 0.150%

    No Known Activations