INDEX

Explanations

words related to geographical locations, specifically those ending in 'in'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in."

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

 Seym

-0.92

 warr

-0.75

 destro

-0.74

hovah

-0.73

 redund

-0.71

 trave

-0.68

¶æ

-0.68

 behav

-0.68

catentry

-0.66

 tremend

-0.65

POSITIVE LOGITS

strument

1.44

flation

1.15

jury

1.14

ned

1.13

aug

1.12

iti

1.11

hibited

1.10

ners

1.09

neapolis

1.09

clusive

1.08

Activations Density 0.049%

words related to geographical locations, specifically those ending in 'in'

occurrences of the word "in."

No Comments

No Known Activations