INDEX

Explanations

comparisons indicating a large difference

oai_token-act-pair · gpt-3.5-turbo

extreme degrees of comparison or emphasis in statements

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

emis

-0.84

icks

-0.74

ription

-0.69

ysis

-0.69

 Peel

-0.69

 Picks

-0.68

ortium

-0.67

piracy

-0.67

ettings

-0.66

olor

-0.65

POSITIVE LOGITS

thing

0.91

fetched

0.87

 enough

0.85

med

0.80

 Enough

0.78

aday

0.73

enough

0.70

itud

0.69

Range

0.69

far

0.67

Activations Density 0.028%

comparisons indicating a large difference

extreme degrees of comparison or emphasis in statements

No Comments

No Known Activations