INDEX

Explanations

specific locations or objects related to physical space or places

oai_token-act-pair · gpt-3.5-turbo

phrases indicating possession or location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

NPR

-0.71

atis

-0.67

inqu

-0.67

araoh

-0.66

official

-0.63

pez

-0.63

ocobo

-0.63

}}}

-0.62

Â¯

-0.60

#$

-0.60

POSITIVE LOGITS

 Grave

0.62

there

0.61

ply

0.60

 Lange

0.60

 Mineral

0.56

 Winged

0.56

 disguised

0.56

 swast

0.56

 renamed

0.54

 converter

0.54

Activations Density 0.555%

specific locations or objects related to physical space or places

phrases indicating possession or location

No Comments

No Known Activations