INDEX

Explanations

specific mentions of events or actions related to law enforcement or emergency situations

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "was" indicating past situations or 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

inav

-0.81

olon

-0.69

 Highlights

-0.67

iates

-0.67

 Telescope

-0.67

arta

-0.67

 entails

-0.66

isms

-0.66

ãĥķãĤ¡

-0.65

 merits

-0.64

POSITIVE LOGITS

 arrested

1.09

 supposed

1.07

 able

1.05

 sentenced

1.02

 transported

1.02

 arra

1.01

 hospitalized

1.00

 killed

0.97

 taken

0.97

 apprehended

0.97

Activations Density 0.261%

specific mentions of events or actions related to law enforcement or emergency situations

instances of the verb "was" indicating past situations or events

No Comments

No Known Activations