INDEX

Explanations

questions or statements expressing uncertainty or the need to gather more information

oai_token-act-pair · gpt-3.5-turbo

statements of uncertainty or knowledge limitations

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

phrine

-0.58

rin

-0.58

plex

-0.58

alia

-0.57

jet

-0.57

TN

-0.56

ctory

-0.56

leted

-0.56

ciating

-0.56

 Parad

-0.55

POSITIVE LOGITS

 definitively

1.21

 anymore

1.15

 whether

1.06

 exactly

1.05

 accurately

1.04

 precisely

0.98

nor

0.98

 exact

0.95

 precise

0.95

 anything

0.94

Activations Density 0.199%

questions or statements expressing uncertainty or the need to gather more information

statements of uncertainty or knowledge limitations

No Comments

No Known Activations