INDEX

Explanations

words related to the concept of "opening."

oai_token-act-pair · gpt-3.5-turbo

references to events or activities that are described as "opening."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

tics

-0.95

cia

-0.91

ieving

-0.81

lean

-0.76

zin

-0.76

bil

-0.74

rag

-0.70

lust

-0.70

rome

-0.69

ka

-0.69

POSITIVE LOGITS

 Doors

0.87

 ceremonies

0.86

 doors

0.84

 opening

0.82

 openings

0.77

 weekend

0.75

 Weekend

0.74

 salv

0.73

 reopen

0.71

 parentheses

0.71

Activations Density 0.023%

words related to the concept of "opening."

references to events or activities that are described as "opening."

No Comments

No Known Activations