INDEX

Explanations

descriptions related to location or place

oai_token-act-pair · gpt-3.5-turbo

sentences that indicate the existence or state of something

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arming

-0.76

angering

-0.73

urden

-0.72

conn

-0.71

Enlarge

-0.67

itement

-0.66

apper

-0.66

ire

-0.65

inge

-0.63

osate

-0.63

POSITIVE LOGITS

 also

1.27

 furthermore

1.15

 therefore

1.08

 additionally

1.04

 moreover

0.95

 located

0.92

 preceded

0.88

 ALSO

0.86

 however

0.86

 advised

0.81

Activations Density 0.480%

descriptions related to location or place

sentences that indicate the existence or state of something

No Comments

No Known Activations