INDEX

Explanations

conditional statements related to taking an action or making a decision

oai_token-act-pair · gpt-3.5-turbo

phrases that express taking action or making decisions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

holm

-0.67

Cong

-0.67

 agre

-0.66

gian

-0.64

ingen

-0.63

eers

-0.63

 Smile

-0.61

eman

-0.60

 Kamp

-0.59

Domain

-0.58

POSITIVE LOGITS

 advantage

1.18

aways

1.13

 heed

0.96

 aback

0.90

 care

0.88

 refuge

0.83

autions

0.82

overs

0.81

OVER

0.80

 precedence

0.79

Activations Density 0.120%

conditional statements related to taking an action or making a decision

phrases that express taking action or making decisions

No Comments

No Known Activations