INDEX

Explanations

obstacles or barriers

oai_token-act-pair · gpt-3.5-turbo

terms related to obstacles and barriers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

liv

-0.68

atorium

-0.68

zsche

-0.68

ream

-0.65

 RELEASE

-0.64

ERAL

-0.63

ffield

-0.62

iren

-0.62

daq

-0.61

 Transcript

-0.61

POSITIVE LOGITS

 preventing

1.13

 obstacle

1.12

 obstacles

1.07

 barriers

1.06

 erected

1.01

 barrier

0.96

 insur

0.96

 blocking

0.96

 impede

0.95

 hurdles

0.94

Activations Density 0.081%

obstacles or barriers

terms related to obstacles and barriers

No Comments

No Known Activations