INDEX

Explanations

phrases related to expressing an opinion or belief

oai_token-act-pair · gpt-3.5-turbo

expressions of capability or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

pires

-0.77

furt

-0.70

soever

-0.68

thing

-0.65

breakers

-0.64

 ancestor

-0.62

senal

-0.60

 revisions

-0.60

 Kinnikuman

-0.59

 Published

-0.58

POSITIVE LOGITS

't

1.60

 assure

1.32

 attest

1.26

 imagine

1.13

 honestly

1.05

 tell

1.04

 guarantee

1.03

 relate

1.03

NOT

1.02

 foresee

1.00

Activations Density 0.080%

phrases related to expressing an opinion or belief

expressions of capability or possibility

No Comments

No Known Activations