INDEX

Explanations

the word "though" in sentences

oai_token-act-pair · gpt-3.5-turbo

the word "though" indicating contrasting or conditional points

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

lees

-0.80

enture

-0.68

inated

-0.67

 WATCHED

-0.62

anu

-0.62

adesh

-0.62

inity

-0.61

ination

-0.61

ragon

-0.61

gaard

-0.61

POSITIVE LOGITS

tons

0.98

 admittedly

0.94

ts

0.85

 interestingly

0.77

 fortunately

0.76

 thankfully

0.76

 curiously

0.71

 technically

0.70

 acknowledging

0.68

still

0.67

Activations Density 0.034%

the word "though" in sentences

the word "though" indicating contrasting or conditional points

No Comments

No Known Activations