INDEX

Explanations

phrases related to specific individuals and their actions or attributes

oai_token-act-pair · gpt-3.5-turbo

unusual characters or symbols that indicate non-standard text elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Entered

-0.73

 Hait

-0.55

 trout

-0.54

 crocod

-0.53

 sacred

-0.53

 wildlife

-0.52

 seismic

-0.51

 spec

-0.51

 shark

-0.50

 sharks

-0.49

POSITIVE LOGITS

ãĤ¦ãĤ¹

0.77

prototype

0.70

*/(

0.69

âĸĳ

0.69

ortment

0.67

FORE

0.62

acon

0.62

ngth

0.61

reciation

0.61

ktop

0.61

Activations Density 2.280%

phrases related to specific individuals and their actions or attributes

unusual characters or symbols that indicate non-standard text elements

No Comments

No Known Activations