INDEX

Explanations

words related to technology and hacking, especially related to computer systems and security

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 't'

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

ĪĴ

-0.73

 destro

-0.72

 resil

-0.71

 tremend

-0.67

 behavi

-0.67

 mosqu

-0.66

 suspic

-0.66

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.65

ãĤĭ

-0.64

çĦ

-0.64

POSITIVE LOGITS

ronics

1.19

ribute

1.19

ractor

1.17

olkien

1.13

ronic

1.12

ruck

1.12

ween

1.11

uple

1.09

roph

1.08

oxin

1.06

Activations Density 0.081%

words related to technology and hacking, especially related to computer systems and security

instances of the letter 't'

No Comments

No Known Activations