INDEX

Explanations

words related to different medical treatments and procedures

oai_token-act-pair · gpt-3.5-turbo

specific character strings or letters with high frequency in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

OPLE

-0.81

 multim

-0.73

FORMATION

-0.68

 butterfly

-0.67

FTWARE

-0.67

$$$$

-0.66

REF

-0.63

 Compass

-0.61

 feathers

-0.61

 gorilla

-0.61

POSITIVE LOGITS

ahn

0.76

ka

0.75

sa

0.74

esh

0.74

hra

0.73

acho

0.73

anas

0.72

ury

0.72

ija

0.72

endra

0.71

Activations Density 0.158%

words related to different medical treatments and procedures

specific character strings or letters with high frequency in the text

No Comments

No Known Activations