INDEX

Explanations

instances of the word "similar" in the text

oai_token-act-pair · gpt-3.5-turbo

references to similar events or situations

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

OST

-0.79

arden

-0.79

UME

-0.70

phasis

-0.69

ribution

-0.67

hest

-0.66

oway

-0.65

@@@@

-0.65

wood

-0.65

 Beans

-0.63

POSITIVE LOGITS

 vein

1.11

 sized

0.96

worldly

0.95

 fate

0.94

minded

0.93

 minded

0.91

 amounts

0.89

 sentiments

0.88

 twins

0.83

lihood

0.82

Activations Density 0.028%

instances of the word "similar" in the text

references to similar events or situations

No Comments

No Known Activations