INDEX

Explanations

terms related to a specific company named AG

oai_token-act-pair · gpt-3.5-turbo

references to a specific entity or organization denoted as "AG"

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

phia

-0.81

thia

-0.80

pite

-0.75

pper

-0.75

perse

-0.72

phrine

-0.72

lihood

-0.70

dates

-0.70

nia

-0.67

licts

-0.67

POSITIVE LOGITS

EMENT

1.15

REE

1.02

ENCY

1.00

HHHH

0.95

ENC

0.89

GR

0.88

VERTISEMENT

0.84

reement

0.83

ENT

0.83

GRE

0.82

Activations Density 0.027%

terms related to a specific company named AG

references to a specific entity or organization denoted as "AG"

No Comments

No Known Activations