INDEX

Explanations

phrases related to making decisions or taking action

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to significant actions or decisions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iolet

-0.66

 teasp

-0.65

dos

-0.65

ailability

-0.62

inia

-0.62

held

-0.61

inav

-0.60

 practition

-0.58

annot

-0.58

employ

-0.57

POSITIVE LOGITS

iest

0.90

liest

0.84

 anew

0.77

 wisely

0.76

 ahead

0.74

 responsibly

0.73

 correctly

0.73

wrong

0.73

osphere

0.73

enium

0.72

Activations Density 0.277%

phrases related to making decisions or taking action

phrases and terms related to significant actions or decisions

No Comments

No Known Activations