INDEX

Explanations

actions or events indicated by the word "called"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "called."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ILCS

-0.66

 trophies

-0.61

 shocks

-0.57

eeds

-0.56

 gaps

-0.55

letico

-0.54

 considerations

-0.54

 ideologies

-0.52

 disparities

-0.51

 compliance

-0.51

POSITIVE LOGITS

 called

3.47

 Called

2.64

called

2.63

 termed

2.36

 dubbed

1.86

 referred

1.83

 named

1.74

 titled

1.65

 nicknamed

1.64

 CALL

1.55

Activations Density 0.037%

actions or events indicated by the word "called"

instances of the word "called."

No Comments

No Known Activations