INDEX

Explanations

legal and regulatory terminology

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

 pretty

-0.57

-0.56

Imagine

-0.52

青

-0.51

mye

-0.51

 really

-0.51

He

-0.50

 just

-0.50

really

-0.50

 Imagine

-0.49

POSITIVE LOGITS

 BoxFit

0.87

StructEnd

0.87

SourceChecksum

0.85

 kasarigan

0.85

\{\\

0.84

aarrggbb

0.83

ModelSerializer

0.82

 صوتيه

0.80

 '\\;'

0.80

."</

0.79

Activations Density 0.545%

legal and regulatory terminology

No Comments

No Known Activations