INDEX

Explanations

words related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

variations of the word "vern" in different contexts

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

raid

-0.79

FTA

-0.71

ARC

-0.67

OHN

-0.65

------------------------------------------------

-0.64

pora

-0.64

Torrent

-0.62

CHR

-0.61

Wan

-0.60

 regrett

-0.60

POSITIVE LOGITS

acular

1.24

sburg

0.90

issance

0.90

ormal

0.88

vironment

0.80

unci

0.79

ote

0.78

icht

0.78

ocity

0.77

ues

0.76

Activations Density 0.019%

words related to geographical locations

variations of the word "vern" in different contexts

No Comments

No Known Activations