INDEX

Explanations

numerical values indicating a significant level or degree of something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "significantly."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

tein

-0.83

ifully

-0.83

nar

-0.81

icip

-0.74

elsen

-0.74

emy

-0.73

aily

-0.73

atu

-0.73

sburgh

-0.73

eer

-0.72

POSITIVE LOGITS

 impacting

1.02

 impacted

0.98

 effected

0.94

 deterior

0.81

 affecting

0.80

 differ

0.79

 influenced

0.78

 affected

0.78

0.77

 degrade

0.75

Activations Density 0.038%

numerical values indicating a significant level or degree of something

instances of the word "significantly."

No Comments

No Known Activations