INDEX

Explanations

references to different contexts in a structured format

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

 uſed

-0.84

omla

-0.81

SBATCH

-0.79

IonicModule

-0.79

 Shakspeare

-0.79

Efq

-0.78

 DELLE

-0.78

ModelAdmin

-0.78

#+#

-0.76

✨:

-0.75

POSITIVE LOGITS

 context

1.69

Context

1.66

 Context

1.65

 useContext

1.63

 contexts

1.60

context

1.57

 CONTEXT

1.55

CONTEXT

1.47

 getContext

1.34

ctx

1.33

Activations Density 0.036%

references to different contexts in a structured format

No Comments

No Known Activations