INDEX

Explanations

phrases or sentences containing the word "like" in a simile or comparison context

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing uniqueness or exceptional qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cannabin

-0.73

idates

-0.69

istries

-0.69

incial

-0.69

idity

-0.67

osterone

-0.63

Published

-0.61

galitarian

-0.59

gerald

-0.59

restling

-0.57

POSITIVE LOGITS

 plague

0.75

 spoiled

0.65

hots

0.61

ãĤ§

0.61

 Ancients

0.60

ahime

0.60

iaz

0.59

ippers

0.59

itaire

0.58

 predecessors

0.58

Activations Density 0.120%

phrases or sentences containing the word "like" in a simile or comparison context

phrases emphasizing uniqueness or exceptional qualities

No Comments

No Known Activations