INDEX

Explanations

references to specific geographic locations preceded by a possessive word

oai_token-act-pair · gpt-3.5-turbo

possessive forms of nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĳå£«

-0.86

ording

-0.83

èĢħ

-0.77

iaries

-0.74

object

-0.73

nels

-0.72

!/

-0.72

linux

-0.72

JECT

-0.71

folios

-0.69

POSITIVE LOGITS

 finest

0.97

 largest

0.93

 newest

0.92

own

0.90

 burgeoning

0.87

 elite

0.86

 wealthiest

0.86

 poorest

0.85

 premier

0.85

 biggest

0.84

Activations Density 0.097%

references to specific geographic locations preceded by a possessive word

possessive forms of nouns

No Comments

No Known Activations