INDEX

Explanations

mentions of specific characters and people related to a narrative or legal context

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

Followed by a capitalized place name

np_acts-logits-general · gemini-2.0-flash

named entities and their context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

istoitu

-0.74

󠁿

-0.66

原始内容存档于

-0.61

ADVERTISEMENT

-0.59

!*\

-0.58

-0.55

__*/

-0.55

WEBPACK

-0.55

FLICT

-0.54

setcounter

-0.53

POSITIVE LOGITS

 pleaſure

1.24

 themſelves

1.23

 myſelf

1.18

 Theſe

1.16

 Reſ

1.14

 whoſe

1.13

 ſeveral

1.13

Efq

1.11

 becauſe

1.11

 himſelf

1.11

Activations Density 1.348%

mentions of specific characters and people related to a narrative or legal context

Followed by a capitalized place name

named entities and their context

No Comments

No Known Activations