INDEX

Explanations

words related to burdens or responsibilities

oai_token-act-pair · gpt-3.5-turbo

mentions of the concept of "burden."

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

naissance

-0.73

*/(

-0.72

specified

-0.71

apeake

-0.69

 rave

-0.68

ebus

-0.67

confirmed

-0.66

encers

-0.66

chlor

-0.66

mpeg

-0.65

POSITIVE LOGITS

 burden

1.39

 burdens

1.28

lessly

0.92

 burd

0.91

 borne

0.84

 load

0.81

 loads

0.79

 levied

0.76

weights

0.74

 incurred

0.72

Activations Density 0.027%

words related to burdens or responsibilities

mentions of the concept of "burden."

No Comments

No Known Activations