INDEX

Explanations

words related to the name "enn."

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 caution

-0.66

 pains

-0.64

 Turtles

-0.60

LOAD

-0.59

 retard

-0.59

 underest

-0.57

ty

-0.57

typ

-0.57

 trickle

-0.56

 Bulg

-0.56

POSITIVE LOGITS

essee

1.24

sylvania

1.13

issance

1.10

esis

1.10

iece

1.09

ihilation

1.09

orable

1.03

edy

1.00

elly

1.00

esse

0.98

Activations Density 0.023%

words related to the name "enn."

references to specific individuals or names

No Comments

No Known Activations