INDEX

Explanations

phrases indicating a correction or additional context to a previous statement or assertion

oai_token-act-pair · gpt-3.5-turbo

assertive statements expressing personal opinions or clarifications

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

stal

-0.72

ipel

-0.72

cellaneous

-0.65

ixt

-0.65

lier

-0.64

¹

-0.63

]:

-0.63

isen

-0.62

backer

-0.62

uten

-0.61

POSITIVE LOGITS

 admittedly

0.99

 disagree

0.87

 technically

0.85

 faults

0.80

 sympath

0.76

 superf

0.74

 laud

0.74

 imperfect

0.72

acity

0.70

 merits

0.69

Activations Density 0.640%

phrases indicating a correction or additional context to a previous statement or assertion

assertive statements expressing personal opinions or clarifications

No Comments

No Known Activations