INDEX

Explanations

mentions of a specific country or collective entity

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "nation" 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 @ 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

omething

-0.82

urations

-0.71

hift

-0.71

IFT

-0.69

wrapper

-0.68

ension

-0.67

err

-0.66

pread

-0.66

Vaj

-0.65

Adds

-0.65

POSITIVE LOGITS

wide

1.07

States

0.75

 sovere

0.75

matically

0.74

ographically

0.73

 legislature

0.72

agog

0.71

ically

0.71

urally

0.70

ographer

0.70

Activations Density 0.028%

mentions of a specific country or collective entity

occurrences of the word "nation" in various contexts

No Comments

No Known Activations