INDEX

Explanations

financial terms and references to ratings agencies

oai_token-act-pair · gpt-3.5-turbo

references to the organization "Standard & Poor's."

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

-0.75

cig

-0.75

 destro

-0.73

resent

-0.70

hig

-0.68

senal

-0.66

cffffcc

-0.66

 wart

-0.66

Unknown

-0.65

shit

-0.64

POSITIVE LOGITS

 deviation

1.11

 deviations

1.01

 Catalog

0.82

 Chart

0.81

ization

0.80

ised

0.77

 Definition

0.77

ity

0.76

 Format

0.76

 Template

0.74

Activations Density 0.011%

financial terms and references to ratings agencies

references to the organization "Standard & Poor's."

No Comments

No Known Activations