INDEX

Explanations

phrases indicating a sequence of events, specifically events that happened just before a certain action or outcome

oai_token-act-pair · gpt-3.5-turbo

pronouns, particularly focusing on the repeated mentions of "he," "she," "I," and "they."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Associated

-0.71

 Monteneg

-0.64

 Canaver

-0.64

 Consortium

-0.64

 Electrical

-0.63

 Federation

-0.63

 Optim

-0.61

 understatement

-0.61

 sarc

-0.61

 Strategy

-0.60

POSITIVE LOGITS

've

1.04

 arrived

0.91

 started

0.87

 began

0.87

're

0.87

hran

0.84

 became

0.82

'd

0.82

 exited

0.82

 arrive

0.82

Activations Density 0.136%

phrases indicating a sequence of events, specifically events that happened just before a certain action or outcome

pronouns, particularly focusing on the repeated mentions of "he," "she," "I," and "they."

No Comments

No Known Activations