INDEX

Explanations

proper nouns or specific names of entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "are" and "were" 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 @ 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

 lapse

-0.75

 diseng

-0.69

onding

-0.67

century

-0.66

bis

-0.65

 guiActiveUnfocused

-0.65

 operation

-0.62

 process

-0.61

 transition

-0.60

 regulate

-0.60

POSITIVE LOGITS

*:

0.83

 staples

0.71

ATHER

0.70

 Cosponsors

0.69

 nods

0.68

 finalists

0.68

ngth

0.68

 representatives

0.66

 namely

0.65

Bey

0.65

Activations Density 0.269%

proper nouns or specific names of entities

occurrences of the phrase "are" and "were" in various contexts

No Comments

No Known Activations