INDEX

Explanations

words related to making choices or decisions

oai_token-act-pair · gpt-3.5-turbo

terms related to making choices or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Danger

-0.70

flies

-0.70

INESS

-0.69

riage

-0.69

 Granger

-0.67

 Worldwide

-0.66

Project

-0.63

Dri

-0.63

Cole

-0.62

ciating

-0.62

POSITIVE LOGITS

opt

1.10

 opting

0.98

 opted

0.93

atory

0.84

uary

0.83

aye

0.76

atis

0.75

imum

0.75

nir

0.73

lect

0.72

Activations Density 0.012%

words related to making choices or decisions

terms related to making choices or decisions

No Comments

No Known Activations