INDEX

Explanations

dialogue and speech-related actions within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 EClass

-0.63

addCriterion

-0.60

 faid

-0.60

 defire

-0.55

دانشنامهٔ

-0.55

saying

-0.55

Multimedia

-0.54

]();

-0.53

 disait

-0.53

proken

-0.53

POSITIVE LOGITS

 referring

0.70

 softly

0.65

EDEFAULT

0.61

 innocently

0.60

 casually

0.59

 calmly

0.58

 sambil

0.58

 after

0.58

DebuggerStep

0.57

 aloud

0.57

Activations Density 0.086%

dialogue and speech-related actions within the text

No Comments

No Known Activations