INDEX

Explanations

specific identifiers or markers associated with data elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

RenderAtEndOf

-0.87

 themſelves

-0.85

 himſelf

-0.82

 purpoſe

-0.82

 itſelf

-0.80

 myſelf

-0.76

€/

-0.76

 uſed

-0.75

 Monfieur

-0.75

 raiſ

-0.74

POSITIVE LOGITS

0.52

sig

0.47

0.46

0.43

0.41

0.40

所示

0.40

Activations Density 0.085%

specific identifiers or markers associated with data elements

No Comments

No Known Activations