INDEX

Explanations

financial terms or concepts

oai_token-act-pair · gpt-3.5-turbo

words related to emotional experiences or conditions

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

etheless

-0.85

 carbohyd

-0.76

 notor

-0.76

 stocking

-0.76

specified

-0.71

 concess

-0.70

 conserv

-0.70

 numbered

-0.69

matically

-0.69

ullivan

-0.68

POSITIVE LOGITS

 Runner

0.90

âĦ¢:

0.86

âĦ¢

0.85

 Valley

0.84

 Tracker

0.84

 Records

0.84

 Zone

0.84

Force

0.83

 Breaker

0.82

 Tactics

0.82

Activations Density 0.260%

financial terms or concepts

words related to emotional experiences or conditions

No Comments

No Known Activations