INDEX

Explanations

phrases indicating understanding, agreement, or comprehension

oai_token-act-pair · gpt-3.5-turbo

statements of comprehension or understanding

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

rouse

-0.76

woods

-0.72

rock

-0.70

strip

-0.69

die

-0.68

metal

-0.67

onies

-0.67

Ranked

-0.67

pload

-0.65

endar

-0.64

POSITIVE LOGITS

 understands

0.74

Duc

0.71

ĺħ

0.71

ible

0.71

 Understand

0.70

 Stafford

0.70

ably

0.69

 Languages

0.68

ances

0.67

iotic

0.67

Activations Density 0.034%

phrases indicating understanding, agreement, or comprehension

statements of comprehension or understanding

No Comments

No Known Activations