INDEX

Explanations

phrases related to future outcomes or consequences

oai_token-act-pair · gpt-3.5-turbo

phrases related to outcomes and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ĸļ

-0.68

tained

-0.66

hess

-0.59

emp

-0.58

²¾

-0.58

oons

-0.57

aq

-0.56

requently

-0.56

ouf

-0.56

aeper

-0.56

POSITIVE LOGITS

 someday

1.15

 sooner

1.06

morrow

1.05

 hopefully

0.98

 Eventually

0.98

Eventually

0.96

Will

0.95

will

0.94

 eventually

0.94

soon

0.94

Activations Density 0.516%

phrases related to future outcomes or consequences

phrases related to outcomes and consequences

No Comments

No Known Activations