INDEX

Explanations

words within parentheses

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "here" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 guiName

-0.86

":[{"

-0.76

."

-0.72

.''

-0.71

();

-0.70

({

-0.67

.''.

-0.67

ãĢĲ

-0.63

.[

-0.63

 (âĪĴ

-0.63

POSITIVE LOGITS

?)

1.77

1.67

?),

1.63

-)

1.61

)."

1.58

)"

1.58

),"

1.58

)/

1.56

?).

1.55

!)

1.54

Activations Density 0.394%

words within parentheses

occurrences of the word "here" and its variants

No Comments

No Known Activations