INDEX

Explanations

pronouns indicating possession, specifically "their."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "their."

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

 Unsure

-0.78

hin

-0.72

mast

-0.70

Bear

-0.70

 Flan

-0.69

zz

-0.67

Thompson

-0.67

scape

-0.66

ean

-0.65

pri

-0.65

POSITIVE LOGITS

 respective

1.53

own

1.50

selves

1.32

 selves

1.16

 predecessors

1.06

 counterparts

1.04

 successors

1.00

 careers

0.96

self

0.96

 namesake

0.95

Activations Density 0.202%

pronouns indicating possession, specifically "their."

occurrences of the word "their."

No Comments

No Known Activations