INDEX

Explanations

comparative questions regarding size or value

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Hochspringen

-0.83

 EdgeInsets

-0.80

DockStyle

-0.74

tvguidetime

-0.72

Geplaatst

-0.67

TypedDataSet

-0.67

complexContent

-0.62

ArgsConstructor

-0.62

 MainAxisSize

-0.60

 محفوظة

-0.60

POSITIVE LOGITS

 whichever

0.63

หว่าง

0.59

 between

0.57

BASELINE

0.55

ParallelGroup

0.54

 közül

0.54

between

0.50

Whether

0.50

hichever

0.50

whether

0.50

Activations Density 0.270%

comparative questions regarding size or value

No Comments

No Known Activations