INDEX

Explanations

references to evidence and claims in legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ResumeLayout

-0.56

AddTagHelper

-0.51

impresa

-0.51

"],

-0.48

llingen

-0.46

шкой

-0.46

tagHelper

-0.45

pheny

-0.43

λεί

-0.41

parseColor

-0.40

POSITIVE LOGITS

具体的な

0.78

 specifying

0.77

 specifics

0.77

具体的

0.76

 specify

0.76

 vague

0.75

 defaultstate

0.75

具体

0.75

 explaining

0.73

 details

0.71

Activations Density 0.694%

references to evidence and claims in legal contexts

No Comments

No Known Activations