INDEX

Explanations

actions or plans conveyed through verbs in the present tense

oai_token-act-pair · gpt-3.5-turbo

phrases associated with waiting or anticipation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 predecessor

-0.56

Cooldown

-0.52

_-

-0.51

ãĥ´ãĤ¡

-0.48

externalActionCode

-0.47

{*

-0.47

 interviewer

-0.47

 presidency

-0.46

 implies

-0.46

Insert

-0.46

POSITIVE LOGITS

 themselves

1.02

 their

0.85

selves

0.83

their

0.82

 THEIR

0.81

 Their

0.76

 collectively

0.75

Their

0.72

 theirs

0.67

represented

0.60

Activations Density 1.197%

actions or plans conveyed through verbs in the present tense

phrases associated with waiting or anticipation

No Comments

No Known Activations