INDEX

Explanations

questions or phrases related to interviews or discussions

oai_token-act-pair · gpt-3.5-turbo

references to questions and inquiries, especially in a structured format

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

senal

-0.73

ufact

-0.69

ngth

-0.67

ãĥ¼ãĤ¯

-0.66

flu

-0.63

Tok

-0.63

 Enemies

-0.60

âķĲâķĲ

-0.60

Spr

-0.59

 Fail

-0.57

POSITIVE LOGITS

answered

0.96

answer

0.93

 unanswered

0.92

 answered

0.90

 trivia

0.86

 answers

0.78

 Answers

0.77

 whether

0.77

Answer

0.77

urger

0.74

Activations Density 0.175%

questions or phrases related to interviews or discussions

references to questions and inquiries, especially in a structured format

No Comments

No Known Activations