INDEX

Explanations

phrases related to public access and availability

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 كومونز

-0.62

featureID

-0.61

transQ

-0.55

isNotNull

-0.55

ceğine

-0.55

SEMICOLON

-0.52

 StringTokenizer

-0.51

 traductions

-0.51

älv

-0.50

imbursement

-0.49

POSITIVE LOGITS

 maneu

1.14

hcm

1.13

 intersper

1.11

 increa

1.10

 reluct

1.09

 secon

1.04

 encomp

1.04

 Sinal

1.03

fuf

1.03

 erad

1.02

Activations Density 0.223%

phrases related to public access and availability

No Comments

No Known Activations