INDEX

Explanations

references to different seasons, episodes, games, and volumes in a series or show

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ught

-0.66

uckland

-0.62

igious

-0.61

 laund

-0.56

 blot

-0.55

Pow

-0.54

 franc

-0.53

 behavi

-0.53

roleum

-0.52

PUT

-0.52

POSITIVE LOGITS

VII

1.17

 VIII

1.17

1.08

1.06

1.03

IX

1.02

1.00

III

1.00

Activations Density 0.167%

references to different seasons, episodes, games, and volumes in a series or show

No Comments

No Known Activations