INDEX

Explanations

mentions of specific locations or proper nouns

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

ностран

-0.61

<bos>

-0.58

:""

-0.57

спользова

-0.57

desertcart

-0.55

ISPR

-0.55

 دیکھیے

-0.55

>);

-0.55

ATEGY

-0.54

AILABILITY

-0.54

POSITIVE LOGITS

aen

1.13

fta

1.11

fte

1.10

 intrigu

1.08

 accla

1.07

 stockholm

1.06

miu

1.06

 franz

1.04

 illi

1.04

 emphat

1.04

Activations Density 0.287%

mentions of specific locations or proper nouns

No Comments

No Known Activations