INDEX

Explanations

words related to values or assessments of things

oai_token-act-pair · gpt-3.5-turbo

references to value and valuation in various contexts

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

pread

-0.78

 EntityItem

-0.68

éĹĺ

-0.67

hower

-0.66

ELF

-0.65

 Daylight

-0.65

batch

-0.64

 Bread

-0.63

olitan

-0.62

soever

-0.60

POSITIVE LOGITS

uations

1.14

ueless

1.12

ibr

1.11

entin

1.04

uing

0.94

enture

0.94

ipers

0.94

orie

0.94

anches

0.93

anche

0.92

Activations Density 0.006%

words related to values or assessments of things

references to value and valuation in various contexts

No Comments

No Known Activations