INDEX

Explanations

phrases that contradict a preceding statement or expectation

oai_token-act-pair · gpt-3.5-turbo

negations and phrases indicating what something is not

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ãģ®ç

-0.73

ngth

-0.69

çīĪ

-0.67

ividual

-0.67

icks

-0.64

éĥ

-0.62

 showc

-0.62

 Links

-0.61

wives

-0.60

agos

-0.60

POSITIVE LOGITS

 necessarily

1.08

 happening

0.91

rael

0.82

 exactly

0.80

icable

0.78

 uncommon

0.78

actly

0.77

 coincidence

0.76

 happ

0.74

 detract

0.73

Activations Density 0.107%

phrases that contradict a preceding statement or expectation

negations and phrases indicating what something is not

No Comments

No Known Activations