INDEX

Explanations

words related to hindering or preventing something

oai_token-act-pair · gpt-3.5-turbo

the word "deter" 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

ammy

-0.78

olini

-0.78

ocene

-0.75

 halls

-0.73

 rooft

-0.67

hetti

-0.65

ioch

-0.64

ocalypse

-0.64

 appointments

-0.62

 openings

-0.60

POSITIVE LOGITS

ministic

1.84

minist

1.50

rence

1.05

gent

1.00

ior

0.96

ring

0.94

ency

0.87

rer

0.87

red

0.86

 deter

0.85

Activations Density 0.018%

words related to hindering or preventing something

the word "deter" in various contexts

No Comments

No Known Activations