INDEX

Explanations

verbs indicating a requirement or obligation

oai_token-act-pair · gpt-3.5-turbo

directives or requirements emphasizing necessary actions

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

MpServer

-0.76

catentry

-0.70

Orig

-0.67

road

-0.64

Jun

-0.64

Twe

-0.63

Disc

-0.62

 Palest

-0.62

Enh

-0.61

Kal

-0.61

POSITIVE LOGITS

 beware

0.87

 yourself

0.80

 understand

0.73

 specify

0.72

 KNOW

0.71

 HAVE

0.71

 know

0.71

 choose

0.71

 learn

0.70

 configure

0.70

Activations Density 0.196%

verbs indicating a requirement or obligation

directives or requirements emphasizing necessary actions

No Comments

No Known Activations