INDEX

Explanations

dates in the format "Month, Year" with high activation values

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

 heapq

-0.67

Nichts

-0.63

 rospy

-0.61

astéro

-0.60

 [''],

-0.59

Gambas

-0.59

אין

-0.59

المنا

-0.59

asteroide

-0.56

 pymongo

-0.56

POSITIVE LOGITS

 sement

0.83

0.82

 monaster

0.77

 frambo

0.76

 kön

0.76

 marte

0.76

 meras

0.75

 vitale

0.71

 vermel

0.71

 utop

0.71

Activations Density 0.058%

dates in the format "Month, Year" with high activation values

No Comments

No Known Activations