INDEX

Explanations

phrases related to legal or illegal actions

oai_token-act-pair · gpt-3.5-turbo

overall sentiment or opinions expressed in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 transition

-0.80

 transitions

-0.77

ishable

-0.76

 abyss

-0.74

thal

-0.74

 optional

-0.71

ishment

-0.71

inous

-0.68

ency

-0.68

 reversible

-0.68

POSITIVE LOGITS

 Though

1.17

 Particularly

1.15

 Instead

1.12

 Especially

1.12

 Earlier

1.11

 Specifically

1.08

 Firstly

1.08

 Whereas

1.07

 While

1.07

 Initially

1.05

Activations Density 0.669%

phrases related to legal or illegal actions

overall sentiment or opinions expressed in the text

No Comments

No Known Activations