INDEX

Explanations

phrases indicating a sense of inclusivity or universality

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "all"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

IDS

-0.61

aminer

-0.60

bal

-0.58

dt

-0.58

 Caption

-0.56

inth

-0.56

oute

-0.56

FG

-0.55

hift

-0.55

ahime

-0.54

POSITIVE LOGITS

ocating

1.18

igator

1.15

uding

1.11

usion

1.04

igators

1.03

usions

0.98

ocated

0.97

udes

0.96

uring

0.93

ocation

0.93

Activations Density 0.074%

phrases indicating a sense of inclusivity or universality

occurrences of the word "all"

No Comments

No Known Activations