INDEX

Explanations

phrases related to summarizing or concluding information

oai_token-act-pair · gpt-3.5-turbo

the phrase "all that" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Interstitial

-0.77

poon

-0.69

OME

-0.68

gee

-0.65

iots

-0.64

onym

-0.63

ãĥ³ãĤ¸

-0.61

ahime

-0.61

mes

-0.61

roth

-0.61

POSITIVE LOGITS

 mattered

1.21

 separates

1.16

 remains

1.13

 survives

1.11

 remained

1.09

 transpired

1.02

 entails

1.01

 exists

1.00

 distinguishes

0.96

 happens

0.91

Activations Density 0.029%

phrases related to summarizing or concluding information

the phrase "all that" in various contexts

No Comments

No Known Activations