INDEX

Explanations

positive sentiments and words related to positivity

oai_token-act-pair · gpt-3.5-turbo

words related to positivity or positive sentiment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

HAEL

-0.72

channelAvailability

-0.72

loo

-0.71

Leod

-0.67

ibaba

-0.67

-0.66

ESH

-0.66

croft

-0.65

ById

-0.65

OME

-0.63

POSITIVE LOGITS

pos

1.02

itivity

1.00

itional

0.95

ited

0.92

fet

0.88

essor

0.88

sembly

0.88

ffer

0.85

itory

0.85

uper

0.85

Activations Density 0.011%

positive sentiments and words related to positivity

words related to positivity or positive sentiment

No Comments

No Known Activations