INDEX

Explanations

statements indicating uncertainty, confusion, or a lack of knowledge

oai_token-act-pair · gpt-3.5-turbo

expressions of uncertainty or confusion about one's situation or knowledge

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Shine

-0.72

 incumb

-0.68

ixel

-0.67

 Shutterstock

-0.63

nov

-0.62

 showcased

-0.61

 undeniably

-0.60

 dexter

-0.56

 impro

-0.56

 appear

-0.56

POSITIVE LOGITS

 anymore

0.75

ulous

0.67

URR

0.66

_>

0.63

soType

0.62

ammad

0.61

aja

0.61

orget

0.61

kered

0.61

aze

0.60

Activations Density 0.353%

statements indicating uncertainty, confusion, or a lack of knowledge

expressions of uncertainty or confusion about one's situation or knowledge

No Comments

No Known Activations