INDEX

Explanations

phrases expressing negation or contradiction

oai_token-act-pair · gpt-3.5-turbo

interrogative phrases indicating denial or negation

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

aly

-0.72

Vers

-0.67

iland

-0.67

cember

-0.65

haul

-0.63

pez

-0.62

tnc

-0.61

umen

-0.61

olen

-0.61

istries

-0.60

POSITIVE LOGITS

nor

0.92

 anymore

0.87

 necessarily

0.73

 anybody

0.72

 anyone

0.71

any

0.67

 slightest

0.67

ndra

0.65

hemy

0.64

}\

0.63

Activations Density 0.037%

phrases expressing negation or contradiction

interrogative phrases indicating denial or negation

No Comments

No Known Activations