INDEX

Explanations

words starting with "ne"

oai_token-act-pair · gpt-3.5-turbo

mentions of "ne" as a prefix in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

AGES

-0.77

ãĤ·ãĥ£

-0.75

hips

-0.68

gerald

-0.67

 Norn

-0.67

 sinks

-0.63

Layout

-0.62

MODE

-0.62

Preview

-0.61

License

-0.60

POSITIVE LOGITS

pher

0.99

arest

0.98

verend

0.90

ccess

0.89

bec

0.86

onymous

0.84

uter

0.83

hovah

0.81

cro

0.81

phan

0.81

Activations Density 0.018%

words starting with "ne"

mentions of "ne" as a prefix in various contexts

No Comments

No Known Activations