INDEX

Explanations

verbs related to providing information or explanations

oai_token-act-pair · gpt-3.5-turbo

instances where previous points or mentions are referenced

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

wcs

-0.76

ãĤ¼ãĤ¦ãĤ¹

-0.73

OPE

-0.70

orest

-0.70

enez

-0.69

 replica

-0.68

erate

-0.68

ctors

-0.67

ealous

-0.65

orah

-0.65

POSITIVE LOGITS

[|

0.75

 Tale

0.74

 Hacker

0.71

TOD

0.71

 newsp

0.70

 Hier

0.68

 commenter

0.67

 Mish

0.67

 spoiler

0.65

 âĺ

0.65

Activations Density 0.182%

verbs related to providing information or explanations

instances where previous points or mentions are referenced

No Comments

No Known Activations