INDEX

Explanations

names of specific entities or locations

oai_token-act-pair · gpt-3.5-turbo

specific names or terms related to food, substances, or popular culture

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

etheless

-0.80

 compr

-0.70

 guid

-0.69

 coron

-0.69

irted

-0.66

ournal

-0.64

ebin

-0.64

 magnification

-0.64

viously

-0.64

ammed

-0.63

POSITIVE LOGITS

 Bowl

0.99

 Games

0.98

 Shop

0.97

 Strip

0.91

 Club

0.91

 Boys

0.90

 Mile

0.89

haus

0.88

finger

0.88

 Balls

0.88

Activations Density 0.203%

names of specific entities or locations

specific names or terms related to food, substances, or popular culture

No Comments

No Known Activations