INDEX

Explanations

adjectives describing uncertainty or fairness

oai_token-act-pair · gpt-3.5-turbo

concepts and terminology related to uncertainty and fairness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

cle

-0.70

STE

-0.66

ynthesis

-0.64

ickr

-0.62

soType

-0.59

 Neuroscience

-0.58

 reperto

-0.58

 Enhancement

-0.58

veland

-0.58

STON

-0.58

POSITIVE LOGITS

ãĤ®

0.75

acy

0.73

gment

0.72

furt

0.72

WARE

0.70

ifiable

0.70

 excuses

0.69

idden

0.68

ustomed

0.66

 anymore

0.65

Activations Density 0.080%

adjectives describing uncertainty or fairness

concepts and terminology related to uncertainty and fairness

No Comments

No Known Activations