INDEX

Explanations

words related to justification or validation

oai_token-act-pair · gpt-3.5-turbo

terms related to validation and justification

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

sites

-0.91

ngth

-0.81

cules

-0.80

pell

-0.79

waves

-0.78

llular

-0.71

pel

-0.70

 athlet

-0.70

duino

-0.69

wp

-0.68

POSITIVE LOGITS

icated

1.13

ication

1.09

 Roosevelt

0.99

iary

0.92

ictive

0.90

icate

0.88

icating

0.86

icates

0.85

ications

0.82

 Kejriwal

0.75

Activations Density 0.086%

words related to justification or validation

terms related to validation and justification

No Comments

No Known Activations