INDEX

Explanations

terms related to internet technology, specifically related to the prefix "inter-"

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to "inter" indicating intersections or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 deaf

-0.70

 deduction

-0.69

uala

-0.64

 Skydragon

-0.63

 peanuts

-0.63

 scratch

-0.62

 shake

-0.61

udeb

-0.60

OPLE

-0.59

 jobs

-0.59

POSITIVE LOGITS

mediate

1.27

ventions

1.24

acting

1.14

rupted

1.14

lude

1.11

vention

1.11

continental

1.11

section

1.10

locking

1.10

actions

1.09

Activations Density 0.019%

terms related to internet technology, specifically related to the prefix "inter-"

words and phrases related to "inter" indicating intersections or connections

No Comments

No Known Activations