INDEX

Explanations

adjectives or phrases that convey a sense of certainty or definitiveness

oai_token-act-pair · gpt-3.5-turbo

phrases indicating specificity or categorization of entities and concepts

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

 partName

-0.77

istries

-0.70

osterone

-0.67

ÄŁ

-0.65

mare

-0.64

 GOODMAN

-0.63

NXT

-0.61

mares

-0.61

ersen

-0.60

abases

-0.58

POSITIVE LOGITS

 progresses

0.95

ociated

0.68

eyes

0.65

 navig

0.61

iru

0.61

 progressed

0.60

devices

0.60

independent

0.60

 relates

0.59

 conduit

0.59

Activations Density 0.292%

adjectives or phrases that convey a sense of certainty or definitiveness

phrases indicating specificity or categorization of entities and concepts

No Comments

No Known Activations