INDEX

Explanations

mentions of airplane crashes

oai_token-act-pair · gpt-3.5-turbo

mentions of "plane" in various contexts

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

laus

-0.92

FINE

-0.78

PUT

-0.76

essee

-0.72

 Cumber

-0.71

shire

-0.70

UGC

-0.68

uces

-0.67

lishes

-0.67

optional

-0.66

POSITIVE LOGITS

walk

1.09

 airliner

1.03

walker

0.98

 prope

0.98

 plane

0.97

 airplanes

0.97

 hangar

0.96

 wreckage

0.94

plane

0.93

 planes

0.93

Activations Density 0.020%

mentions of airplane crashes

mentions of "plane" in various contexts

No Comments

No Known Activations