INDEX

Explanations

verbs related to actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

verbs indicating actions or behaviors

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

Campaign

-0.65

ãĥķãĤ©

-0.65

crim

-0.61

Applic

-0.60

ãĤ±

-0.59

berus

-0.59

 APPLIC

-0.59

winner

-0.58

theless

-0.58

affer

-0.57

POSITIVE LOGITS

 theirs

0.91

 themselves

0.84

 alike

0.78

ingly

0.74

 their

0.70

eth

0.67

 parach

0.65

 Hitchcock

0.64

aldehyde

0.61

oba

0.61

Activations Density 0.422%

verbs related to actions or behaviors

verbs indicating actions or behaviors

No Comments

No Known Activations