INDEX

Explanations

instances where the word "sat" is used in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "sat."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ISO

-0.69

Operation

-0.68

#$

-0.67

credit

-0.67

ALLY

-0.67

 Failure

-0.64

allows

-0.64

ever

-0.63

enforcement

-0.63

taining

-0.63

POSITIVE LOGITS

chel

1.04

chers

0.90

anic

0.87

olith

0.85

ivas

0.84

 seiz

0.84

lie

0.84

cher

0.83

chell

0.81

anism

0.80

Activations Density 0.011%

instances where the word "sat" is used in various contexts

instances of the word "sat."

No Comments

No Known Activations