INDEX

Explanations

monetary values or financial terms

oai_token-act-pair · gpt-3.5-turbo

phrases related to exceptions or exclusions in data

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

rouse

-0.80

SPONSORED

-0.78

Sym

-0.77

Kind

-0.76

mire

-0.73

ERN

-0.72

vic

-0.71

gging

-0.71

 largeDownload

-0.70

SCP

-0.69

POSITIVE LOGITS

 outl

0.94

 caveats

0.86

 taxes

0.75

 deductions

0.72

enhagen

0.71

 overtime

0.70

VAT

0.70

 inflation

0.70

 Nielsen

0.69

 comparisons

0.69

Activations Density 0.170%

monetary values or financial terms

phrases related to exceptions or exclusions in data

No Comments

No Known Activations