INDEX

Explanations

mentions of specific characters or places

oai_token-act-pair · gpt-3.5-turbo

instances of a specific non-standard character or symbol in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Mirage

-0.67

 mounts

-0.67

 trail

-0.65

 intersections

-0.63

 Seah

-0.63

 reflex

-0.62

 avenues

-0.61

 strengths

-0.60

 yield

-0.59

 pleasures

-0.59

POSITIVE LOGITS

ï¸ı

1.22

ternity

0.96

#$

0.93

uthor

0.93

amily

0.90

Occup

0.86

Û

0.86

\-

0.85

Â£

0.84

Activations Density 0.171%

mentions of specific characters or places

instances of a specific non-standard character or symbol in the text

No Comments

No Known Activations