INDEX

Explanations

mentions of a specific entity or organization starting with the letter "F" and followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "F" 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 @ 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

vier

-0.69

 Conquest

-0.68

 Twain

-0.67

 Boone

-0.66

 Aether

-0.65

 Hades

-0.64

 Reborn

-0.63

 Clever

-0.62

 Hera

-0.61

 Heights

-0.61

POSITIVE LOGITS

ocused

1.21

ruits

1.21

ortunate

1.17

avour

1.17

ocusing

1.17

ortun

1.16

andom

1.13

ertility

1.12

isher

1.10

iddler

1.10

Activations Density 0.043%

mentions of a specific entity or organization starting with the letter "F" and followed by a numerical value

occurrences of the letter "F" in various contexts

No Comments

No Known Activations