INDEX

Explanations

phrases or statements indicating a requirement for a specific action or condition

oai_token-act-pair · gpt-3.5-turbo

the term "required" in various contexts and forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

vironment

-0.89

cow

-0.76

imir

-0.74

apest

-0.69

lique

-0.69

ells

-0.68

ned

-0.68

venture

-0.67

oleon

-0.67

stead

-0.67

POSITIVE LOGITS

 prerequisite

0.78

 unanim

0.78

 aback

0.75

 ingredient

0.74

 redund

0.74

obe

0.70

 introdu

0.70

 sshd

0.69

 guiActiveUn

0.69

 requirement

0.67

Activations Density 0.024%

phrases or statements indicating a requirement for a specific action or condition

the term "required" in various contexts and forms

No Comments

No Known Activations