INDEX

Explanations

examples and instances in the context of data or scenarios

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

 samples

-0.63

enumii

-0.62

 SAMPLES

-0.61

 sample

-0.58

StoryboardSegue

-0.58

 protoimpl

-0.57

sample

-0.56

 sampel

-0.55

XMLSchema

-0.55

sampling

-0.53

POSITIVE LOGITS

 taken

0.70

 illustrating

0.64

taken

0.57

Taken

0.54

 seder

0.53

 tiré

0.53

 TAKEN

0.53

 showing

0.53

 kasus

0.52

 montrant

0.51

Activations Density 0.246%

examples and instances in the context of data or scenarios

No Comments

No Known Activations