INDEX

Explanations

mentions of credit ratings

oai_token-act-pair · gpt-3.5-turbo

references to credit ratings and their evaluations

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

IFrame

Link

Negative Logits

adr

-0.81

ansson

-0.77

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.73

Alz

-0.73

hers

-0.72

nuts

-0.71

stasy

-0.70

cling

-0.69

clus

-0.67

working

-0.67

POSITIVE LOGITS

 rating

1.23

 ratings

1.14

 Ratings

1.00

 Rating

0.94

Rating

0.88

rating

0.85

 downgrade

0.80

âĺħâĺħ

0.79

 rated

0.79

 score

0.77

Activations Density 0.023%

mentions of credit ratings

references to credit ratings and their evaluations

No Known Activations