INDEX

Explanations

references to immediate actions or effects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

intenant

-0.74

 विश्वसनीयता

-0.63

 dépens

-0.60

 médié

-0.60

 mukaan

-0.59

 coû

-0.59

scribers

-0.59

찮

-0.58

BeginContext

-0.58

 réguli

-0.57

POSITIVE LOGITS

 số

2.45

 Số

1.43

sô

1.42

Số

1.25

ố

0.88

数

0.71

DataAnnotations

0.66

數

0.66

StructEnd

0.60

Ố

0.58

Activations Density 0.066%

references to immediate actions or effects

No Comments

No Known Activations