INDEX

Explanations

expressions of personal belief or opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 apparently

-1.15

 Apparently

-1.07

Apparently

-1.04

 reportedly

-1.02

apparently

-1.01

 allegedly

-0.96

 supposedly

-0.96

 seemingly

-0.88

 supuestamente

-0.87

 schein

-0.85

POSITIVE LOGITS

 underrated

0.77

 overrated

0.77

 underestimated

0.77

 unfairly

0.74

StructEnd

0.72

पया

0.72

 préférable

0.71

 wisest

0.71

 CascadeType

0.71

 raisonnable

0.70

Activations Density 0.248%

expressions of personal belief or opinion

No Comments

No Known Activations