INDEX

Explanations

assessments of performance or evaluations of quality

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

Tikang

-0.87

esModule

-0.82

endphp

-0.76

 nonUne

-0.72

出版年

-0.71

 שוליים

-0.71

COUVER

-0.69

 '\\;'

-0.69

 isComment

-0.67

POSITIVE LOGITS

job

2.22

job

1.82

Job

1.69

Job

1.67

JOB

1.60

JOB

1.40

 jobs

1.39

jobs

1.21

 Jobs

1.16

 jobb

1.15

Activations Density 0.087%

assessments of performance or evaluations of quality

No Comments

No Known Activations