INDEX

Explanations

references to SD cards and related technical details.

oai_token-act-pair · gpt-3.5-turbo

terms related to SD cards and their specifications

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

htar

-0.79

pins

-0.74

ghazi

-0.69

mingham

-0.67

heading

-0.66

awaru

-0.65

pin

-0.65

cham

-0.64

 deaf

-0.63

 pregnant

-0.62

POSITIVE LOGITS

LP

1.10

IFF

1.08

SD

0.97

CC

0.96

IVERS

0.96

HC

0.95

ARS

0.92

ocument

0.92

DEN

0.90

ouble

0.88

Activations Density 0.022%

**references to SD cards and related technical details.**

terms related to SD cards and their specifications

No Comments

No Known Activations

references to SD cards and related technical details.