INDEX

Explanations

references to personal pronouns and articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 دیکھیے

-0.60

 houſe

-0.55

 referrerpolicy

-0.55

 समीक्षाओं

-0.53

ſelves

-0.52

 Ragh

-0.52

seamnă

-0.52

AddTagHelper

-0.51

شهاد

-0.50

 Houſe

-0.50

POSITIVE LOGITS

den

0.66

formik

0.64

findpost

0.63

RenderAtEndOf

0.60

det

0.54

 biri

0.52

pions

0.51

 Ours

0.51

cloudfront

0.51

Ours

0.49

Activations Density 0.051%

references to personal pronouns and articles

No Comments

No Known Activations