INDEX

Explanations

verbs indicating significant impact or influence

oai_token-act-pair · gpt-3.5-turbo

actions or events that lead to significant consequences

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

 tweet

-0.67

 Tobacco

-0.64

 Introdu

-0.63

 Tweet

-0.60

 Firearms

-0.59

NON

-0.58

 NEVER

-0.57

 LOOK

-0.56

 STAND

-0.56

 References

-0.55

POSITIVE LOGITS

hift

0.85

psey

0.78

vantage

0.72

 tremend

0.72

 havoc

0.72

 inex

0.70

kefeller

0.69

akable

0.69

veyard

0.69

uced

0.67

Activations Density 0.291%

verbs indicating significant impact or influence

actions or events that lead to significant consequences

No Comments

No Known Activations