INDEX

Explanations

words with the term "so-called."

oai_token-act-pair · gpt-3.5-turbo

phrases that include the term "so-called," indicating a skepticism or critique of labels or classifications

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

=-=-=-=-

-0.90

=-=-=-=-=-=-=-=-

-0.82

erves

-0.78

 unden

-0.78

=-=-

-0.76

 istg

-0.74

 destro

-0.69

*=-

-0.69

Ö¼

-0.68

 proport

-0.67

POSITIVE LOGITS

called

0.83

erred

0.82

untarily

0.77

holes

0.72

metadata

0.72

calling

0.72

amn

0.72

call

0.71

unt

0.70

nant

0.69

Activations Density 0.023%

words with the term "so-called."

phrases that include the term "so-called," indicating a skepticism or critique of labels or classifications

No Comments

No Known Activations