INDEX

Explanations

terms related to interaction or interface design

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "inter"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\\\\\\\\

-0.77

 tremend

-0.75

¶ħ

-0.74

ORK

-0.67

avorite

-0.67

EStream

-0.66

ggies

-0.65

 Skydragon

-0.64

unks

-0.64

aimon

-0.63

POSITIVE LOGITS

mediate

1.01

ventions

0.90

active

0.88

action

0.83

vention

0.81

mitt

0.80

acting

0.80

continental

0.79

medi

0.76

section

0.75

Activations Density 0.007%

terms related to interaction or interface design

occurrences of the word "inter"

No Comments

No Known Activations