INDEX

Explanations

proper nouns and names

oai_token-act-pair · gpt-3.5-turbo

actions described by verbs related to formal decisions, announcements, and legislative activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

pmwiki

-0.70

nig

-0.65

.[

-0.64

phys

-0.64

.–

-0.63

 anymore

-0.63

 dement

-0.62

fuck

-0.61

dirty

-0.61

."[

-0.60

POSITIVE LOGITS

 earlier

0.91

 Wednesday

0.86

 yesterday

0.85

 Thursday

0.84

 Tuesday

0.82

 last

0.80

 Monday

0.79

 interim

0.76

 initial

0.75

 Friday

0.72

Activations Density 0.463%

proper nouns and names

actions described by verbs related to formal decisions, announcements, and legislative activities

No Comments

No Known Activations