INDEX

Explanations

specific mentions of locations

oai_token-act-pair · gpt-3.5-turbo

the definite article "the" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

pointers

-0.71

load

-0.69

quit

-0.68

ibl

-0.68

fn

-0.68

arians

-0.68

handedly

-0.68

pers

-0.65

POSE

-0.65

ional

-0.64

POSITIVE LOGITS

 midst

1.44

 aftermath

1.30

 vicinity

1.29

 meantime

1.23

 Philippines

1.15

 guise

1.14

 wake

1.12

 absence

1.07

 same

1.07

 Netherlands

0.97

Activations Density 0.345%

specific mentions of locations

the definite article "the" in various contexts

No Comments

No Known Activations