INDEX

Explanations

instances of the word "letter."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "letter" in various contexts

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

rolet

-0.72

negie

-0.69

 Occupations

-0.69

 Tune

-0.65

 CCTV

-0.63

 STATS

-0.61

runs

-0.60

engeance

-0.60

liga

-0.58

rises

-0.58

POSITIVE LOGITS

Letter

0.96

 addressed

0.94

 letter

0.92

 sent

0.87

velop

0.87

 penned

0.86

 mailed

0.82

letter

0.81

boxing

0.81

 letters

0.80

Activations Density 0.035%

instances of the word "letter."

occurrences of the word "letter" in various contexts

No Comments

No Known Activations