INDEX

Explanations

phrases related to locations or place names

oai_token-act-pair · gpt-3.5-turbo

instances of the word "let."

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

 cumbers

-1.02

DAY

-0.77

PLIED

-0.75

manship

-0.73

 tremend

-0.72

VERTISEMENT

-0.70

 resil

-0.69

peria

-0.67

PUT

-0.66

 holiest

-0.65

POSITIVE LOGITS

tered

1.01

ting

1.01

ariat

0.99

oad

0.96

rack

0.86

own

0.84

opia

0.84

tering

0.83

ons

0.83

ocol

0.83

Activations Density 0.015%

phrases related to locations or place names

instances of the word "let."

No Comments

No Known Activations