INDEX

Explanations

phrases related to detection, identification, and prediction in various fields such as medicine, technology, and security

oai_token-act-pair · gpt-3.5-turbo

terms related to detection and identification processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ĸļ

-1.04

è£ħ

-0.78

©¶æ¥µ

-0.77

ãĤ´ãĥ³

-0.75

ember

-0.70

}}}

-0.67

amon

-0.67

usa

-0.66

stanbul

-0.66

amera

-0.66

POSITIVE LOGITS

 anomalies

0.97

 vulnerabilities

0.93

 weaknesses

0.90

 anomal

0.90

 faults

0.88

 whether

0.88

 patterns

0.86

 deficiencies

0.85

 defects

0.85

 potential

0.84

Activations Density 0.178%

phrases related to detection, identification, and prediction in various fields such as medicine, technology, and security

terms related to detection and identification processes

No Comments

No Known Activations