INDEX

Explanations

numerical quantities and temporal indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 approximately

-0.60

-0.59

-0.56

-0.54

-0.53

-0.51

POSITIVE LOGITS

Rhestr

0.87

 itſelf

0.79

CloseOperation

0.77

IUrlHelper

0.74

 myſelf

0.73

 halfway

0.73

 dozen

0.72

StructEnd

0.71

enumi

0.71

ंदीखरीदारी

0.71

Activations Density 0.270%

numerical quantities and temporal indicators

No Comments

No Known Activations