INDEX

Explanations

tokens that represent commands or instructions

oai_token-act-pair · gpt-3.5-turbo

individual letters or character sequences that signify text or code elements

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

Ae

-0.76

 Chosen

-0.69

 undert

-0.69

 Stones

-0.67

 Founding

-0.66

 Rolls

-0.65

idation

-0.65

 Standing

-0.65

 Manifest

-0.65

 Thrones

-0.64

POSITIVE LOGITS

td

1.11

tg

1.10

vc

1.08

dm

1.05

pg

1.01

sb

1.01

fw

1.00

sf

0.99

tp

0.99

vl

0.97

Activations Density 0.188%

tokens that represent commands or instructions

individual letters or character sequences that signify text or code elements

No Comments

No Known Activations