INDEX

Explanations

phrases related to geographical locations, particularly straits

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Straits" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Authorities

-0.67

flies

-0.64

 theorem

-0.62

ause

-0.60

ICA

-0.60

oration

-0.60

ale

-0.59

 helpers

-0.58

 secretaries

-0.58

gdala

-0.57

POSITIVE LOGITS

pping

1.24

pped

1.21

fing

1.12

ights

1.05

pless

1.05

ÃŁ

0.99

ppers

0.97

pper

0.94

ppy

0.93

ighter

0.92

Activations Density 0.020%

phrases related to geographical locations, particularly straits

occurrences of the name "Straits" and its variations

No Comments

No Known Activations