INDEX

Explanations

levels of substances or elements in relation to studies, reports, and test results

oai_token-act-pair · gpt-3.5-turbo

references to levels of substances or measurements in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

issance

-0.74

orial

-0.67

roe

-0.63

 genre

-0.61

sov

-0.60

ctors

-0.60

stars

-0.58

 identities

-0.58

ads

-0.57

 genres

-0.57

POSITIVE LOGITS

 detectable

0.80

 concentrations

0.78

 levels

0.76

 measured

0.76

etting

0.76

elsius

0.76

 readings

0.74

 attained

0.72

mberg

0.71

 detected

0.71

Activations Density 0.063%

levels of substances or elements in relation to studies, reports, and test results

references to levels of substances or measurements in various contexts

No Comments

No Known Activations