INDEX

Explanations

the name "Joe" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Joe."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

hips

-0.82

raints

-0.81

 glim

-0.79

mble

-0.79

igators

-0.77

HCR

-0.72

igated

-0.72

NESS

-0.71

dayName

-0.71

igator

-0.70

POSITIVE LOGITS

 Biden

0.95

Rog

0.87

zzi

0.84

 Arpaio

0.82

 Camel

0.81

ppo

0.80

 Walsh

0.79

 Danger

0.78

 Crow

0.75

Ra

0.75

Activations Density 0.010%

the name "Joe" in various contexts

occurrences of the name "Joe."

No Comments

No Known Activations