INDEX

Explanations

terms related to inquiries or investigations

oai_token-act-pair · gpt-3.5-turbo

words related to inquiries or investigations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Depend

-0.80

nown

-0.73

berman

-0.71

artifacts

-0.64

 martyr

-0.61

 Mehran

-0.60

Cod

-0.60

 Nadu

-0.58

perm

-0.58

enburg

-0.58

POSITIVE LOGITS

 Inqu

1.24

 inquire

1.21

iry

1.11

iries

1.08

 inqu

1.05

isition

1.02

 enqu

1.01

 inquired

1.00

naires

0.97

isitions

0.97

Activations Density 0.029%

terms related to inquiries or investigations

words related to inquiries or investigations

No Comments

No Known Activations