INDEX

Explanations

phrases related to behaviors or actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "actions" in relation to moral responsibility or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

bid

-0.73

BLE

-0.65

AES

-0.65

mbuds

-0.64

 Dise

-0.64

orf

-0.62

inately

-0.62

ondo

-0.61

used

-0.61

definition

-0.60

POSITIVE LOGITS

uations

1.05

 ACTIONS

0.99

uate

0.98

 actions

0.95

uated

0.89

uation

0.89

uary

0.86

hops

0.85

uating

0.84

ives

0.81

Activations Density 0.025%

phrases related to behaviors or actions

instances of the word "actions" in relation to moral responsibility or consequences

No Comments

No Known Activations