INDEX

Explanations

words related to lists or items in a list

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

 reluct

-0.67

 Godt

-0.66

 horrend

-0.66

 unspeak

-0.65

 spartan

-0.64

 cuck

-0.62

 spind

-0.60

 enthusi

-0.59

 celtic

-0.59

 apprehen

-0.59

POSITIVE LOGITS

•

0.87

•

0.82

.•

0.71

)•

0.69

••

0.68

("")]

0.64

°•

0.61

·

0.58

~•

0.58

(::

0.57

Activations Density 0.108%

words related to lists or items in a list

No Comments

No Known Activations