INDEX

Explanations

instructions related to app functionality and customization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 tartalomajánló

-0.49

sio

-0.46

 représentation

-0.45

 Shet

-0.45

communic

-0.45

 zobra

-0.45

 Taras

-0.45

multirow

-0.44

läs

-0.44

kula

-0.44

POSITIVE LOGITS

 editing

0.97

 effects

0.96

 filters

0.95

 Effects

0.93

 Filters

0.89

 edit

0.85

 edits

0.85

 Editing

0.83

Effects

0.82

effects

0.81

Activations Density 0.303%

instructions related to app functionality and customization

No Comments

No Known Activations