INDEX

Explanations

the word "Sydney" with high activations, potentially in different contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Sydney" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 caution

-0.76

 resolve

-0.75

 perfect

-0.68

 pity

-0.66

ãĥ´ãĤ¡

-0.63

OPER

-0.63

Ã§a

-0.62

 confidence

-0.61

éĹĺ

-0.61

perture

-0.61

POSITIVE LOGITS

yd

0.99

aniel

0.98

rox

0.95

roid

0.91

ynamic

0.91

essert

0.91

elta

0.91

roxy

0.90

ield

0.86

eez

0.85

Activations Density 0.004%

the word "Sydney" with high activations, potentially in different contexts

occurrences of the word "Sydney" and its variations

No Comments

No Known Activations