INDEX

Explanations

references to bows or bow-related activities

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

UnusedPrivate

-0.67

 besk

-0.63

 nakalista

-0.61

 Duggan

-0.61

 huesos

-0.60

TRIBUN

-0.59

fikation

-0.58

hept

-0.58

 Robbins

-0.57

\|^{

-0.57

POSITIVE LOGITS

bow

1.38

 bows

1.16

bow

1.13

Bow

1.08

Bow

1.06

BOW

0.93

 bowed

0.91

bows

0.90

 bowing

0.87

BOW

0.85

Activations Density 0.615%

references to bows or bow-related activities

No Comments

No Known Activations