INDEX

Explanations

verbs that indicate taking action or causing an effect

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate actions related to achieving goals or acquiring knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

eping

-0.67

 Dresden

-0.67

 Travels

-0.65

ãĤ´ãĥ³

-0.64

 slashed

-0.63

houses

-0.60

attering

-0.59

tto

-0.58

wed

-0.58

ItemTracker

-0.58

POSITIVE LOGITS

oca

0.69

ermanent

0.65

 refres

0.65

ealous

0.62

 nutshell

0.60

izoph

0.59

 properly

0.59

oulos

0.59

ISE

0.59

 qualify

0.58

Activations Density 0.097%

verbs that indicate taking action or causing an effect

phrases that indicate actions related to achieving goals or acquiring knowledge

No Comments

No Known Activations