INDEX

Explanations

verbs related to actively searching for something

oai_token-act-pair · gpt-3.5-turbo

words related to searching or pursuing something

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

EStreamFrame

-0.70

heartedly

-0.70

amination

-0.68

rome

-0.67

itone

-0.64

spin

-0.63

etheless

-0.62

minus

-0.60

ICAN

-0.60

oslov

-0.60

POSITIVE LOGITS

 unsuccessfully

0.76

 refuge

0.74

 seeking

0.73

 seekers

0.71

 revenge

0.70

ache

0.68

lessly

0.68

 opportunities

0.68

WARD

0.68

zag

0.68

Activations Density 0.031%

verbs related to actively searching for something

words related to searching or pursuing something

No Comments

No Known Activations