INDEX

Explanations

phrases where something is being referred to or mentioned

oai_token-act-pair · gpt-3.5-turbo

instances of the word "referred."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

alach

-0.80

EMS

-0.64

iddler

-0.64

EFF

-0.63

;;;;

-0.62

Password

-0.61

OUNT

-0.61

eland

-0.60

IFT

-0.60

ECD

-0.60

POSITIVE LOGITS

 referred

1.05

interstitial

0.91

 Refer

0.85

entious

0.83

 aloud

0.83

 refer

0.82

 references

0.78

 dispar

0.75

 Referred

0.74

irect

0.74

Activations Density 0.009%

phrases where something is being referred to or mentioned

instances of the word "referred."

No Comments

No Known Activations