INDEX

Explanations

adjectives describing intensity or strength

oai_token-act-pair · gpt-3.5-turbo

references to intense competition or conflict

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

ulhu

-0.82

uration

-0.77

eret

-0.71

iture

-0.70

annis

-0.70

ajor

-0.70

abad

-0.69

pty

-0.67

akeru

-0.65

äºĶ

-0.65

POSITIVE LOGITS

ãĥ£

0.98

 fierce

0.93

ly

0.91

 fiercely

0.86

 earthqu

0.85

 battles

0.80

 ferocious

0.80

 streak

0.80

 battle

0.77

 peaks

0.75

Activations Density 0.023%

adjectives describing intensity or strength

references to intense competition or conflict

No Comments

No Known Activations