INDEX

Explanations

prepositions followed by words related to comparison

oai_token-act-pair · gpt-3.5-turbo

comparative phrases or structures

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

Winged

-0.72

-0.71

@@

-0.70

ï¿½ï¿½ï¿½ï¿½

-0.67

aghan

-0.63

ramid

-0.62

Lic

-0.61

ï¿½ï¿½

-0.60

 Revision

-0.58

"></

-0.58

POSITIVE LOGITS

pired

0.89

 advertised

0.85

 readily

0.85

 strongly

0.78

 much

0.77

 usual

0.77

far

0.77

yet

0.76

 favorably

0.75

 evidenced

0.75

Activations Density 0.083%

prepositions followed by words related to comparison

comparative phrases or structures

No Comments

No Known Activations