INDEX

Explanations

pronouns referring to a group or a subject

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the pronoun "They."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CCC

-0.77

ige

-0.73

 Eleven

-0.68

VW

-0.62

cgi

-0.62

atana

-0.61

âĺħâĺħ

-0.60

grid

-0.59

DAY

-0.59

busters

-0.59

POSITIVE LOGITS

're

1.11

'll

1.03

'd

0.92

've

0.90

self

0.86

selves

0.86

zbollah

0.83

 reluct

0.82

pherd

0.81

miah

0.77

Activations Density 0.194%

pronouns referring to a group or a subject

repeated mentions of the pronoun "They."

No Comments

No Known Activations