INDEX

Explanations

indicators of strong emotions or high intensity situations

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

strings of characters that resemble random symbols and letters

oai_token-act-pair · gpt-3.5-turbo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 footing

-0.67

 leaping

-0.59

 deductions

-0.59

 reneg

-0.58

run

-0.58

 dangling

-0.57

restling

-0.57

 grouping

-0.57

 ropes

-0.57

lling

-0.57

POSITIVE LOGITS

rawdownloadcloneembedreportprint

0.97

Posted

0.94

ccording

0.92

Loading

0.91

Emb

0.91

STER

0.89

Author

0.88

Reviewed

0.87

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.85

Product

0.84

Activations Density 0.129%

indicators of strong emotions or high intensity situations

strings of characters that resemble random symbols and letters

No Comments

No Known Activations