INDEX

Explanations

words indicating a shift or change in a situation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating changes in status or transformation over time

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LOCK

-0.67

LLOW

-0.64

 purse

-0.58

 worthy

-0.57

MC

-0.56

 deserve

-0.55

 bodily

-0.55

Champ

-0.53

 Logged

-0.53

Sik

-0.53

POSITIVE LOGITS

uddenly

1.01

 suddenly

0.84

today

0.75

iott

0.74

apult

0.72

instead

0.69

emer

0.69

 reversed

0.69

artney

0.68

nox

0.67

Activations Density 0.624%

words indicating a shift or change in a situation

phrases indicating changes in status or transformation over time

No Comments

No Known Activations