INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the verb "was"

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

arta

-0.80

Footnote

-0.69

 Statements

-0.64

 Plenty

-0.62

feel

-0.61

 Millions

-0.60

 HAVE

-0.60

 Fighters

-0.59

 Mountains

-0.58

arms

-0.58

POSITIVE LOGITS

 originally

1.45

 conceived

1.33

 initially

1.19

 designed

1.16

 discovered

1.15

 born

1.13

 created

1.11

 awarded

1.11

 devised

1.11

 introduced

1.10

Activations Density 0.302%

proper nouns

occurrences of the verb "was"

No Comments

No Known Activations