INDEX

Explanations

phrases related to providing support or reinforcement

oai_token-act-pair · gpt-3.5-turbo

phrases related to support and backing in arguments or claims

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

Ĥİ

-0.67

killed

-0.66

ograms

-0.65

ilet

-0.64

antis

-0.63

resp

-0.63

soDeliveryDate

-0.63

orks

-0.62

eez

-0.62

ppers

-0.60

POSITIVE LOGITS

 presumption

0.80

 belief

0.79

 assumption

0.75

 conviction

0.73

ament

0.72

weights

0.71

 Belief

0.70

 disbelief

0.69

 inference

0.69

lined

0.67

Activations Density 0.415%

phrases related to providing support or reinforcement

phrases related to support and backing in arguments or claims

No Comments

No Known Activations