INDEX

Explanations

phrases related to proving or providing evidence for something

oai_token-act-pair · gpt-3.5-turbo

references to evidence and concepts related to proof

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

BuyableInstoreAndOnline

-0.76

 ILCS

-0.74

nets

-0.72

 Unsure

-0.71

jan

-0.70

ieties

-0.70

 Walters

-0.68

bill

-0.67

 Rout

-0.67

 Manson

-0.67

POSITIVE LOGITS

 validity

0.87

 accomplishment

0.82

 legitimacy

0.81

 authenticity

0.81

 excellence

0.77

 rationality

0.77

 efficacy

0.77

independence

0.75

 neutrality

0.74

 equival

0.74

Activations Density 0.146%

phrases related to proving or providing evidence for something

references to evidence and concepts related to proof

No Comments

No Known Activations