INDEX

Explanations

positive words or descriptions

oai_token-act-pair · gpt-3.5-turbo

words related to positivity and positive sentiment

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

loo

-0.90

HAEL

-0.77

tracks

-0.72

æĸ¹

-0.71

 Brilliant

-0.71

stall

-0.70

ONEY

-0.68

Leod

-0.68

croft

-0.64

OPS

-0.64

POSITIVE LOGITS

itional

1.33

itivity

1.17

itions

1.15

itory

1.05

idon

1.03

itor

0.99

essions

0.98

ited

0.96

itives

0.96

ession

0.92

Activations Density 0.028%

positive words or descriptions

words related to positivity and positive sentiment

No Comments

No Known Activations