INDEX

Explanations

years related to significant events or achievements

oai_token-act-pair · gpt-3.5-turbo

references to specific years related to events or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abulary

-0.81

hes

-0.73

ansk

-0.69

hed

-0.69

APH

-0.67

 suppliers

-0.64

 ancest

-0.64

arf

-0.64

anguage

-0.63

 shutter

-0.59

POSITIVE LOGITS

 Rookie

1.20

 playoffs

1.03

-'

1.03

 season

0.92

 Playoffs

0.86

 rookie

0.85

 offseason

0.84

 postseason

0.84

eco

0.81

 playoff

0.80

Activations Density 0.137%

years related to significant events or achievements

references to specific years related to events or statistics

No Comments

No Known Activations