INDEX

Explanations

references to the word "this" in various contexts

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

olesale

-1.01

^(@)

-0.97

Efq

-0.96

%\]

-0.95

(\<

-0.93

BibitemShut

-0.92

 Paglinawan

-0.90

 Theſe

-0.90

)}]{

-0.89

\]

-0.89

POSITIVE LOGITS

this

1.96

 this

1.10

This

0.97

0.93

if

0.83

THIS

0.81

 This

0.80

you

0.80

self

0.80

that

0.78

Activations Density 0.008%

references to the word "this" in various contexts

No Comments

No Known Activations