INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

names of individuals and their associated titles or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

pport

-0.78

 conver

-0.75

 taxing

-0.66

 rigged

-0.66

 visas

-0.64

 traps

-0.64

 kits

-0.64

 misunder

-0.64

 constraints

-0.63

 overwhelming

-0.63

POSITIVE LOGITS

Jr

1.41

Sr

1.17

PhD

1.12

MD

1.04

 Editor

0.97

Jr

0.96

 Founder

0.94

 Photographer

0.94

 Writer

0.92

aka

0.91

Activations Density 0.165%

names of individuals

names of individuals and their associated titles or roles

No Comments

No Known Activations