INDEX

Explanations

fear or regret related to past events that the individual wishes to avoid in the future

oai_token-act-pair · gpt-3.5-turbo

phrases involving the concept of recurrence or repetition

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

anooga

-0.74

OTS

-0.69

SEA

-0.68

kees

-0.67

emet

-0.66

latest

-0.65

ometric

-0.65

kee

-0.65

 parap

-0.64

HT

-0.63

POSITIVE LOGITS

 someday

0.79

 Dialogue

0.73

nir

0.69

abil

0.69

 conclud

0.69

atile

0.69

 Generations

0.68

soever

0.67

:-)

0.66

 nostalg

0.63

Activations Density 0.024%

fear or regret related to past events that the individual wishes to avoid in the future

phrases involving the concept of recurrence or repetition

No Comments

No Known Activations