INDEX

Explanations

words related to underground activities or settings

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "under" in various contexts

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

ãĥ£

-0.83

Tik

-0.73

 Edison

-0.72

IER

-0.71

andowski

-0.70

ILY

-0.70

eln

-0.69

 Retrieved

-0.69

ilial

-0.68

illac

-0.67

POSITIVE LOGITS

graduate

1.08

cover

1.01

dogs

1.01

whelming

1.01

wear

0.98

lings

0.98

pants

0.96

ground

0.96

lying

0.96

cuts

0.92

Activations Density 0.036%

words related to underground activities or settings

references to the concept of "under" in various contexts

No Comments

No Known Activations