INDEX

Explanations

comparisons or evaluations using the word "seem"

oai_token-act-pair · gpt-3.5-turbo

phrases that express perceptions or judgments about the seeming nature of things

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

 Sabb

-0.65

 revolt

-0.61

ogh

-0.60

 Sabbath

-0.60

âĵĺ

-0.58

redo

-0.57

loads

-0.57

)].

-0.55

isin

-0.55

 learns

-0.55

POSITIVE LOGITS

 innocuous

0.82

 superf

0.81

 daunting

0.77

loo

0.68

 blush

0.67

 harmless

0.66

aiden

0.66

 altru

0.66

 benign

0.66

 confusing

0.64

Activations Density 0.069%

comparisons or evaluations using the word "seem"

phrases that express perceptions or judgments about the seeming nature of things

No Comments

No Known Activations