INDEX

Explanations

claims or assertions being made in the text

oai_token-act-pair · gpt-3.5-turbo

references to assertions and claims regarding social or political issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

foreseen

-0.79

endars

-0.74

 wills

-0.71

keys

-0.70

 Lumpur

-0.70

artney

-0.67

thumbnails

-0.67

ioch

-0.67

 Skydragon

-0.65

NetMessage

-0.65

POSITIVE LOGITS

 uttered

0.92

argument

0.91

 debunked

0.89

 dispro

0.87

 assertion

0.84

 premise

0.84

 refuted

0.84

 asserted

0.82

 vehemently

0.80

ument

0.78

Activations Density 0.179%

claims or assertions being made in the text

references to assertions and claims regarding social or political issues

No Comments

No Known Activations