INDEX

Explanations

mentions of meetings or decision-making situations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "at" in various contexts

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

 benefited

-0.63

eria

-0.60

Russ

-0.59

gered

-0.58

FTWARE

-0.57

indu

-0.57

ptions

-0.55

 opioids

-0.55

 Ahead

-0.54

 ousted

-0.54

POSITIVE LOGITS

 least

1.13

 anytime

1.00

mosp

0.95

 intervals

0.94

las

0.92

 dusk

0.91

 times

0.88

onement

0.87

 noon

0.86

yp

0.86

Activations Density 0.169%

mentions of meetings or decision-making situations

occurrences of the word "at" in various contexts

No Comments

No Known Activations