INDEX

Explanations

phrases related to modes of transportation

oai_token-act-pair · gpt-3.5-turbo

references to modes of transportation and spatial arrangements

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

ibaba

-0.88

endas

-0.67

 neighb

-0.65

 rubbed

-0.65

 seiz

-0.64

ourt

-0.64

 compr

-0.63

orrect

-0.63

vind

-0.63

agara

-0.61

POSITIVE LOGITS

 srfAttach

0.77

 mile

0.64

 intermediary

0.63

Magikarp

0.63

 ingestion

0.60

 chronological

0.60

lining

0.59

 Codec

0.59

loading

0.58

 exhaustion

0.58

Activations Density 0.214%

phrases related to modes of transportation

references to modes of transportation and spatial arrangements

No Comments

No Known Activations