INDEX

Explanations

instances where amounts of money are involved

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

few

-0.82

deck

-0.76

aroo

-0.72

edly

-0.69

aldi

-0.68

station

-0.67

HAEL

-0.66

btn

-0.65

PASS

-0.65

rer

-0.65

POSITIVE LOGITS

effic

0.98

 excess

0.96

 total

0.93

 cash

0.93

 dollars

0.93

 revenue

0.85

 terms

0.83

 increments

0.82

efficiency

0.82

 favor

0.82

Activations Density 0.082%

instances where amounts of money are involved

occurrences of the word "in" used in various contexts

No Comments

No Known Activations