INDEX

Explanations

code structures related to error handling and system capabilities

oai_token-act-pair · gpt-3.5-turbo

nested function calls and expressions in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Schro

-0.68

 Volvo

-0.66

ĸļ

-0.64

Ys

-0.64

 Guantanamo

-0.63

Ã¶n

-0.61

 Stories

-0.61

ificantly

-0.60

 Scandinav

-0.60

 Definitive

-0.59

POSITIVE LOGITS

 DEBUG

0.77

existing

0.76

==

0.73

defined

0.72

needed

0.71

msg

0.69

<=

0.68

null

0.65

any

0.64

Activations Density 0.026%

code structures related to error handling and system capabilities

nested function calls and expressions in programming code

No Comments

No Known Activations