INDEX

Explanations

terms related to sensitivity and how it affects various contexts

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

 divertimento

-0.68

:✨

-0.65

lot

-0.62

 Evers

-0.62

gl

-0.60

кто

-0.60

 braw

-0.59

 felizes

-0.59

 posta

-0.59

weilen

-0.58

POSITIVE LOGITS

 sensitive

1.48

 Sensitive

1.47

Sensitive

1.39

 sensi

1.32

 vulnerability

1.32

 sensitivity

1.32

sensitive

1.28

 sensitivities

1.28

 vulnerabilities

1.20

 Sensitivity

1.19

Activations Density 0.260%

terms related to sensitivity and how it affects various contexts

No Comments

No Known Activations