INDEX

Explanations

verbs or phrases related to actions or events in a historical or informative context

oai_token-act-pair · gpt-3.5-turbo

verbs and phrases related to accusations and assertions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soType

-0.84

stack

-0.79

*/(

-0.74

Sensor

-0.73

AppData

-0.72

bite

-0.71

Bed

-0.69

Mom

-0.67

thank

-0.67

Drop

-0.66

POSITIVE LOGITS

 formatting

0.72

itled

0.69

 nudity

0.68

 mention

0.67

hov

0.66

 humor

0.66

 foreigners

0.66

 references

0.64

 specifically

0.64

 homosexuality

0.63

Activations Density 0.520%

verbs or phrases related to actions or events in a historical or informative context

verbs and phrases related to accusations and assertions

No Comments

No Known Activations