INDEX

Explanations

years, particularly focusing on the year 1983

oai_token-act-pair · gpt-3.5-turbo

references to the year 1983 and related historical context

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

hop

-0.76

hed

-0.72

edge

-0.70

unders

-0.68

edo

-0.64

 lawy

-0.64

 entirety

-0.63

bow

-0.61

Ship

-0.61

iant

-0.59

POSITIVE LOGITS

ixties

0.76

å¹

0.74

-'

0.70

 Schwarzenegger

0.70

 ï¿½ï¿½ï¿½ï¿½

0.69

ãĥ¼

0.65

orporated

0.65

nikov

0.65

 Gandhi

0.65

ICT

0.63

Activations Density 0.035%

years, particularly focusing on the year 1983

references to the year 1983 and related historical context

No Comments

No Known Activations