INDEX

Explanations

references to the name "Carson" in various contexts, including legal cases, food, and personal names

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

 Tull

-0.89

 Anja

-0.76

 McCormick

-0.74

блиоте

-0.72

Anja

-0.72

λλα

-0.70

forName

-0.70

APE

-0.70

es

-0.69

DEX

-0.68

POSITIVE LOGITS

 Carson

0.84

 Viro

0.84

 corks

0.82

 Philadel

0.82

Carson

0.81

 Sion

0.77

enegal

0.75

 setOpen

0.73

 Galla

0.73

 mohair

0.73

Activations Density 1.622%

references to the name "Carson" in various contexts, including legal cases, food, and personal names

No Comments

No Known Activations