INDEX

Explanations

locations or specific places mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

specific names and entities related to people, places, and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

cause

-0.76

>:

-0.71

¶ħ

-0.69

************

-0.67

uala

-0.66

etheless

-0.65

anova

-0.65

imester

-0.65

pherd

-0.64

ivating

-0.64

POSITIVE LOGITS

 resides

0.89

 resided

0.75

 happens

0.74

 intersect

0.74

 supposedly

0.71

 shines

0.69

 enters

0.69

 disemb

0.68

 happened

0.68

 ostensibly

0.68

Activations Density 0.314%

locations or specific places mentioned in the text

specific names and entities related to people, places, and events

No Comments

No Known Activations