INDEX

Explanations

words ending in "ep"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ep"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 nomine

-0.80

 referen

-0.79

âĸ¬

-0.77

ãĤ´ãĥ³

-0.74

 adolesc

-0.74

////////////////

-0.73

 glim

-0.71

ModLoader

-0.71

Ô

-0.68

 unbeliev

-0.68

POSITIVE LOGITS

isodes

1.36

ublic

1.21

stakes

1.20

rint

1.14

odcast

1.13

iphany

1.13

edia

1.10

artment

1.08

hemer

1.04

osit

1.01

Activations Density 0.016%

words ending in "ep"

occurrences of the substring "ep"

No Comments

No Known Activations