INDEX

Explanations

terms and structures associated with GitHub repositories and programming elements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.63

-0.62

“

-0.61

-0.57

ContentAsync

-0.55

分ほど

-0.53

flashdata

-0.52

pre

-0.51

POSITIVE LOGITS

 itſelf

1.24

 houſe

1.19

 purpoſe

1.17

Efq

1.15

 Reſ

1.11

ſelf

1.09

 themſelves

1.08

 Houſe

1.08

 Chriſt

1.07

 pleaſure

1.07

Activations Density 0.009%

terms and structures associated with GitHub repositories and programming elements

No Comments

No Known Activations