INDEX

Explanations

terms related to the beginning of events or actions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a temporal context or the beginning of events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

webkit

-0.65

usercontent

-0.60

 blot

-0.59

æ³

-0.59

houses

-0.59

?:

-0.56

ros

-0.55

 notwithstanding

-0.55

 Walters

-0.55

 wastes

-0.55

POSITIVE LOGITS

 hostilities

0.86

requisite

0.80

thood

0.77

requisites

0.72

ahime

0.71

uberty

0.66

ventory

0.66

earch

0.64

enium

0.63

phase

0.63

Activations Density 0.090%

terms related to the beginning of events or actions

phrases that indicate a temporal context or the beginning of events

No Comments

No Known Activations