INDEX

Explanations

superlatives indicating the best or the most

oai_token-act-pair · gpt-3.5-turbo

superlative adjectives and phrases related to prominence or effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Indra

-0.66

pas

-0.63

raine

-0.61

zek

-0.60

 Mahm

-0.59

anism

-0.58

clusions

-0.58

ipt

-0.57

hots

-0.57

 Seym

-0.57

POSITIVE LOGITS

hest

0.91

 practicable

0.86

 possible

0.81

liest

0.79

 bidder

0.75

est

0.74

 conceivable

0.74

 allowable

0.73

 bang

0.72

 amount

0.72

Activations Density 0.195%

superlatives indicating the best or the most

superlative adjectives and phrases related to prominence or effectiveness

No Comments

No Known Activations