INDEX

Explanations

specific references to a city or location within longer passages

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

.</

-0.79

 thereof

-0.79

.''

-0.78

.","

-0.75

.ï¿½

-0.73

."

-0.72

 thereby

-0.72

elaide

-0.71

.[

-0.70

thood

-0.67

POSITIVE LOGITS

oret

1.02

resa

0.99

 Clintons

0.96

 simplest

0.93

 latest

0.90

 aforementioned

0.90

 biggest

0.89

 toughest

0.85

odore

0.85

 hardest

0.85

Activations Density 1.034%

specific references to a city or location within longer passages

occurrences of the word "the."

No Comments

No Known Activations