INDEX

Explanations

instances of the word "two."

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

own

-0.07

ãĥĥãĤ¯

-0.06

IMARY

-0.06

 twist

-0.06

mol

-0.06

iy

-0.06

 enough

-0.06

ena

-0.06

own

-0.06

POSITIVE LOGITS

Minute

0.06

Ð¾Ð»Ð°Ð¹

0.06

alten

0.06

Cancelable

0.06

OTS

0.06

_DL

0.06

 aforementioned

0.06

ÑīÐµÐ¹

0.06

.latest

0.06

nÄĽ

0.06

Activations Density 0.087%

instances of the word "two."

No Comments

No Known Activations