INDEX

Explanations

phrases consisting of a word followed by " he said."

oai_token-act-pair · gpt-3.5-turbo

statements and quotations from speakers

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

ãĥİ

-0.79

 shitty

-0.61

animate

-0.60

ãĥ¼ãĥĨãĤ£

-0.60

 Birthday

-0.59

 crappy

-0.59

 magically

-0.58

 Kardash

-0.57

 EVERY

-0.56

 steroids

-0.56

POSITIVE LOGITS

 spokeswoman

0.78

ulty

0.77

 spokesman

0.75

0.74

 Reuters

0.70

 cited

0.69

iannopoulos

0.68

 Cheong

0.67

 scathing

0.67

IDER

0.66

Activations Density 0.424%

phrases consisting of a word followed by " he said."

statements and quotations from speakers

No Comments

No Known Activations