INDEX

Explanations

words related to algorithms, mathematical concepts, or computer programming

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.49

Claudia

-0.49

 Claudia

-0.47

HasIndex

-0.47

קישורים

-0.46

Pá

-0.45

twimg

-0.45

HideInInspector

-0.45

Abril

-0.44

SizeMode

-0.44

POSITIVE LOGITS

Fer

1.37

Fer

1.29

FER

1.26

fer

1.13

 ferret

1.07

 Fergus

1.06

fer

1.04

 Ferrell

1.01

 FERR

1.00

 Ferguson

0.99

Activations Density 0.120%

words related to algorithms, mathematical concepts, or computer programming

No Comments

No Known Activations