INDEX

Explanations

advertisements within a text

oai_token-act-pair · gpt-3.5-turbo

occurrences of advertisements within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

grass

-0.70

Kut

-0.67

 Triangle

-0.65

 Roses

-0.61

ãĥ¼ãĥĨãĤ£

-0.60

 Ultr

-0.59

 incarn

-0.58

stood

-0.58

 masse

-0.57

Klu

-0.56

POSITIVE LOGITS

ADVERTISEMENT

1.05

Skip

1.01

iciary

0.80

 Appears

0.78

 Thanks

0.77

 Continued

0.73

iseum

0.70

ILA

0.69

olson

0.69

VERTISEMENT

0.68

Activations Density 0.009%

advertisements within a text

occurrences of advertisements within the text

No Comments

No Known Activations