INDEX

Explanations

phrases indicating doubt or uncertainty

oai_token-act-pair · gpt-3.5-turbo

the repeated phrase "whether" indicating questions of uncertainty or debate

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

Catalog

-0.80

Eye

-0.69

 Caption

-0.68

oscopic

-0.67

Vision

-0.67

icker

-0.67

viks

-0.67

UX

-0.65

wich

-0.65

 Quart

-0.64

POSITIVE LOGITS

soever

0.88

erey

0.67

ornia

0.64

 legitimacy

0.63

 they

0.63

terday

0.63

fy

0.62

 servic

0.61

 respondents

0.61

thood

0.60

Activations Density 0.029%

phrases indicating doubt or uncertainty

the repeated phrase "whether" indicating questions of uncertainty or debate

No Comments

No Known Activations