INDEX

Explanations

names of famous individuals or characters commonly associated with a specific movie or franchise

oai_token-act-pair · gpt-3.5-turbo

characters and names from various forms of entertainment media

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Reviewed

-0.68

mouse

-0.67

ources

-0.64

 Krug

-0.64

 rooting

-0.62

 steer

-0.60

mitt

-0.60

xual

-0.59

orescent

-0.58

[*]

-0.58

POSITIVE LOGITS

etus

0.96

oglu

0.81

nova

0.79

onen

0.79

zona

0.77

esi

0.75

atari

0.73

Lago

0.72

hyde

0.69

ensis

0.67

Activations Density 0.605%

names of famous individuals or characters commonly associated with a specific movie or franchise

characters and names from various forms of entertainment media

No Comments

No Known Activations