INDEX

Explanations

instances of the word "wrap" and its variations, indicating a focus on wrapping or enclosing actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 AssemblyCulture

-1.14

IUrlHelper

-0.86

 noires

-0.83

 <=",

-0.83

 Stuhl

-0.81

 Petersburg

-0.80

 Cardano

-0.79

 Eich

-0.79

 nakalista

-0.77

PSU

-0.76

POSITIVE LOGITS

 wrap

2.22

 wraps

2.16

 Wrap

2.15

 Wraps

2.08

 wrapping

2.07

wrap

2.05

 wrapped

1.97

Wrap

1.97

 wrappers

1.95

Wra

1.93

Activations Density 0.076%

instances of the word "wrap" and its variations, indicating a focus on wrapping or enclosing actions

No Comments

No Known Activations