INDEX

Explanations

occurrences of specific formatting or structured information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

__':

-0.79

OrBuilder

-0.70

TGA

-0.69

FieldBuilder

-0.68

TGA

-0.67

 VizieR

-0.67

PLN

-0.66

 Justine

-0.65

HomeAsUp

-0.65

omenclature

-0.65

POSITIVE LOGITS

SS

2.77

ss

2.59

SS

2.50

ss

2.38

Ss

1.60

Ss

1.54

SSS

1.54

ess

1.48

sss

1.43

SSS

1.41

Activations Density 0.130%

occurrences of specific formatting or structured information

No Comments

No Known Activations