INDEX

Explanations

the words "I", "think", "not", and the pronoun "you"

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

 territo

-1.00

 augus

-0.93

 lele

-0.86

uhr

-0.85

 parlamento

-0.84

 parati

-0.83

 monaster

-0.81

 masaj

-0.81

 moza

-0.81

 kado

-0.79

POSITIVE LOGITS

 apprehen

0.65

จึง

0.62

 hopefully

0.62

 unavoid

0.58

 naturally

0.57

 disreg

0.56

 understandably

0.56

 unspeak

0.55

 presumably

0.55

 assume

0.53

Activations Density 0.141%

the words "I", "think", "not", and the pronoun "you"

No Comments

No Known Activations