INDEX

Explanations

phrases related to communication or reporting

oai_token-act-pair · gpt-3.5-turbo

quoted speech and references to individuals making statements

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

grad

-0.64

Wiz

-0.62

 Purple

-0.62

Vict

-0.61

âĶĢâĶĢâĶĢâĶĢ

-0.60

verts

-0.60

phys

-0.59

 penet

-0.58

bedroom

-0.57

IVERS

-0.57

POSITIVE LOGITS

rite

0.73

arta

0.73

edom

0.70

pherd

0.70

 oversaw

0.70

 echoed

0.69

 advised

0.69

 oversees

0.68

itage

0.68

imon

0.67

Activations Density 0.525%

phrases related to communication or reporting

quoted speech and references to individuals making statements

No Comments

No Known Activations