INDEX

Explanations

phrases involving quoted sources or attributions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "The"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 stagn

-0.71

loading

-0.70

 endeav

-0.68

lication

-0.67

 behalf

-0.66

thood

-0.63

 slowing

-0.63

 stopping

-0.63

 recite

-0.63

 beware

-0.63

POSITIVE LOGITS

odor

1.17

 Huffington

1.11

 Economist

1.10

 Hague

1.10

oret

1.10

 Guardian

1.07

resa

1.07

 Chronicle

1.05

atre

1.02

 Week

0.99

Activations Density 0.067%

phrases involving quoted sources or attributions

occurrences of the word "The"

No Comments

No Known Activations