INDEX

Explanations

words related to notable landmarks and locations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate significant events or actions, particularly destructive actions

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

xual

-0.83

 scrap

-0.80

onte

-0.75

 Blackwell

-0.70

 deaf

-0.69

 grap

-0.64

nces

-0.63

 hospital

-0.63

itives

-0.63

 unaccount

-0.62

POSITIVE LOGITS

?????-?????-

0.94

inventoryQuantity

0.93

Section

0.89

 Âł Âł Âł Âł

0.89

Every

0.83

ccording

0.83

Sometimes

0.82

Unless

0.81

Everyone

0.79

 guiName

0.79

Activations Density 0.333%

words related to notable landmarks and locations

phrases that indicate significant events or actions, particularly destructive actions

No Comments

No Known Activations