INDEX

Explanations

mentions of advertisements, especially with strong emotional or impactful connotations

oai_token-act-pair · gpt-3.5-turbo

mentions of advertisements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Wright

-0.67

 speculative

-0.66

 Myers

-0.62

 survival

-0.61

Hou

-0.60

 Purg

-0.58

 tandem

-0.57

vette

-0.57

 sclerosis

-0.57

hold

-0.56

POSITIVE LOGITS

igmatic

1.08

ads

1.04

ync

1.00

oras

0.98

enza

0.96

venture

0.95

apter

0.95

olph

0.94

vertisements

0.89

ules

0.86

Activations Density 0.007%

mentions of advertisements, especially with strong emotional or impactful connotations

mentions of advertisements

No Comments

No Known Activations