INDEX

Explanations

formal expressions indicating uncertainty or possibility

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce uncertainty or speculation

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

natureconservancy

-0.88

arthed

-0.76

verty

-0.75

vance

-0.74

"},"

-0.73

ocaust

-0.73

ËĪ

-0.72

kees

-0.71

seller

-0.69

efer

-0.68

POSITIVE LOGITS

 someday

0.98

 unsurprisingly

0.78

 sensing

0.75

 Tomorrow

0.69

 opio

0.67

 impeachment

0.67

 suppose

0.66

 millenn

0.64

 tempted

0.64

 fate

0.62

Activations Density 0.043%

formal expressions indicating uncertainty or possibility

phrases that introduce uncertainty or speculation

No Comments

No Known Activations