INDEX

Explanations

terms related to reliability and trustworthiness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

pad

-0.74

éc

-0.73

Pad

-0.68

 createSlice

-0.65

 speeches

-0.64

twimg

-0.63

Scher

-0.62

 Condens

-0.62

pad

-0.61

Pad

-0.61

POSITIVE LOGITS

 reliance

1.21

 reliability

1.19

 Rely

1.18

verläs

1.17

Reliable

1.15

 Reliance

1.14

 Reli

1.11

 relied

1.11

Trusted

1.10

 relying

1.09

Activations Density 0.087%

terms related to reliability and trustworthiness

No Comments

No Known Activations