INDEX

Explanations

phrases indicating possible outcomes or hypothetical situations

oai_token-act-pair · gpt-3.5-turbo

modal verbs expressing possibility or uncertainty

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

iling

-0.64

HT

-0.61

OTA

-0.61

Introduced

-0.60

package

-0.59

 Shots

-0.58

 Odyssey

-0.57

oller

-0.56

 traveler

-0.56

oway

-0.55

POSITIVE LOGITS

 raining

0.94

etsk

0.83

beh

0.78

iner

0.74

 unclear

0.74

 easier

0.72

ÃĥÃĤ

0.71

 culmin

0.67

 dawn

0.67

ZX

0.66

Activations Density 0.304%

phrases indicating possible outcomes or hypothetical situations

modal verbs expressing possibility or uncertainty

No Comments

No Known Activations