INDEX

Explanations

proper nouns related to various entities or characters, potentially searching for a specific entity called "Zeds."

oai_token-act-pair · gpt-3.5-turbo

pluralized nouns and related derivations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ATIONS

-0.71

ASED

-0.71

ATIONAL

-0.70

BIL

-0.70

ALLY

-0.69

ABLE

-0.69

âĸ¬

-0.67

ment

-0.67

ctors

-0.64

 srfAttach

-0.63

POSITIVE LOGITS

mith

1.44

ucker

1.34

hift

1.33

ilver

1.24

pace

1.20

aurus

1.19

hips

1.17

linger

1.16

uits

1.16

paces

1.10

Activations Density 0.164%

proper nouns related to various entities or characters, potentially searching for a specific entity called "Zeds."

pluralized nouns and related derivations

No Comments

No Known Activations