INDEX

Explanations

terms related to "re-" prefixes indicating repetition, revision, or restoration

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

Tokens starting with "Re" or "RE"

np_acts-logits-general · gemini-2.0-flash

words starting with Re

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

TagHelper

-0.73

 AssemblyCulture

-0.69

brenner

-0.62

endpush

-0.61

شهاد

-0.58

gonic

-0.57



-0.56

ResponseWriter

-0.55

tagext

-0.52

TypeDef

-0.52

POSITIVE LOGITS

RE

0.88

Re

0.85

Re

0.84

 Reim

0.74

RE

0.68

Rew

0.64

REC

0.63

RefreshLayout

0.62

Rec

0.62

re

0.61

Activations Density 0.614%

terms related to "re-" prefixes indicating repetition, revision, or restoration

Tokens starting with "Re" or "RE"

words starting with Re

No Comments

No Known Activations

terms related to "re-" prefixes indicating repetition, revision, or restoration

Tokens starting with "Re" or "RE"

words starting with Re

No Comments

No Known Activations