INDEX

Explanations

verbs related to analyzing, speculating, or evaluating outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases indicating conflict, change, and critical evaluation of situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

robe

-0.69

ufact

-0.66

bill

-0.65

ench

-0.63

artney

-0.61

amina

-0.61

nik

-0.58

 Bride

-0.58

apon

-0.57

ouver

-0.57

POSITIVE LOGITS

 causation

0.72

 Corker

0.67

 abound

0.67

 omission

0.65

ãĥ¼ãĥĨ

0.64

 unanswered

0.63

 Rosenstein

0.62

Background

0.62

 bias

0.61

 nonetheless

0.60

Activations Density 2.364%

verbs related to analyzing, speculating, or evaluating outcomes

phrases indicating conflict, change, and critical evaluation of situations

No Comments

No Known Activations