INDEX

Explanations

phrases related to claims of authenticity or credibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-0.65

 surroundings

-0.61

 poff

-0.58

coor

-0.55

 itſelf

-0.54

Reuse

-0.53

 poffible

-0.52

 leaft

-0.52

 pleaſure

-0.52

InstrumentedTest

-0.51

POSITIVE LOGITS

 ostensibly

0.94

 replete

0.88

 touted

0.87

 penchant

0.81

 fraught

0.81

 variously

0.79

 burgeoning

0.78

 esche

0.77

 lauded

0.77

 purported

0.75

Activations Density 2.351%

phrases related to claims of authenticity or credibility

No Comments

No Known Activations