INDEX

Explanations

phrases indicating discrepancies or differences, particularly in the context of representation and expectations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 CreateTagHelper

-0.59

-------------</

-0.52

__':

-0.52

RegressionTest

-0.51

hauer

-0.47

Trag

-0.47

Trouble

-0.47

наче

-0.46

Manbalar

-0.46

 fortæller

-0.46

POSITIVE LOGITS

 varies

0.80

 vary

0.77

 Vary

0.72

fois

0.72

may

0.72

 Varies

0.70

vary

0.69

 ممکن

0.69

varies

0.68

may

0.65

Activations Density 0.175%

phrases indicating discrepancies or differences, particularly in the context of representation and expectations

No Comments

No Known Activations