INDEX

Explanations

phrases referring to a significant amount or portion of something

oai_token-act-pair · gpt-3.5-turbo

repetitive mentions of the word "much."

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

ovie

-0.86

esome

-0.81

ysc

-0.80

allows

-0.76

anski

-0.76

ogens

-0.76

emy

-0.76

agate

-0.75

ologies

-0.75

ades

-0.74

POSITIVE LOGITS

ado

0.88

 meaningful

0.77

 appreciated

0.74

 else

0.72

NESS

0.72

 interest

0.72

 unspecified

0.71

 esteemed

0.70

 convincing

0.69

 simpler

0.69

Activations Density 0.061%

phrases referring to a significant amount or portion of something

repetitive mentions of the word "much."

No Comments

No Known Activations