INDEX

Explanations

phrases related to discussions or arguments

oai_token-act-pair · gpt-3.5-turbo

sentences that convey finality or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 quir

-0.81

 unsus

-0.81

 swiftly

-0.80

 hastily

-0.74

 furiously

-0.74

 brightly

-0.74

 discern

-0.73

 satell

-0.73

 subur

-0.72

 disemb

-0.72

POSITIVE LOGITS

And

1.51

 Somebody

1.49

 Obviously

1.47

 Everybody

1.47

 Because

1.44

So

1.44

 Whereas

1.42

 That

1.41

 Yeah

1.38

 They

1.38

Activations Density 0.320%

phrases related to discussions or arguments

sentences that convey finality or conclusions

No Comments

No Known Activations