INDEX

Explanations

phrases related to inclusion, encompassing everything or everyone

oai_token-act-pair · gpt-3.5-turbo

references to the word "all" in various contexts

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

rir

-0.69

IDS

-0.69

 nowhere

-0.67

SHIP

-0.65

 Schwe

-0.60

aminer

-0.60

 tremend

-0.60

potion

-0.59

nom

-0.59

cule

-0.56

POSITIVE LOGITS

ocating

1.25

iances

1.21

 kinds

1.11

iance

1.10

igator

1.06

 sorts

1.05

ocation

1.04

usions

1.04

ocations

1.03

igators

1.03

Activations Density 0.139%

phrases related to inclusion, encompassing everything or everyone

references to the word "all" in various contexts

No Comments

No Known Activations