INDEX

Explanations

phrases describing observations or perceptions

oai_token-act-pair · gpt-3.5-turbo

phrases that express perception or subjective opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arta

-0.84

opus

-0.81

veland

-0.74

itus

-0.73

cedented

-0.70

heed

-0.69

isa

-0.68

por

-0.68

holm

-0.67

orio

-0.67

POSITIVE LOGITS

 initially

0.70

 hoped

0.68

DEV

0.67

 earlier

0.66

 originally

0.66

 Soviet

0.64

 previously

0.63

 unsuccessfully

0.62

 tremend

0.58

 prog

0.56

Activations Density 0.543%

phrases describing observations or perceptions

phrases that express perception or subjective opinions

No Comments

No Known Activations