INDEX

Explanations

terms related to responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HandlerContext

-0.56

RenderAtEndOf

-0.54

 ThemeData

-0.53

 kasarigan

-0.53

copyWith

-0.52

ItemBackground

-0.50

tonic

-0.50

 subsp

-0.49

สือ

-0.48

 Rendez

-0.48

POSITIVE LOGITS

sibilities

0.85

aarrggbb

0.72

 مرئيه

0.64

sibili

0.61

Lähteet

0.60

sibil

0.55

 zeich

0.54

UpInside

0.53

ChildScrollView

0.52

sib

0.52

Activations Density 0.188%

terms related to responsibilities

No Comments

No Known Activations