INDEX

Explanations

financial entities or terms, particularly the S&P index

oai_token-act-pair · gpt-3.5-turbo

references to the Standard & Poor's (S&P) stock index

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

taboola

-1.01

 thirds

-0.74

=-=-=-=-

-0.74

æ©

-0.73

 GOODMAN

-0.71

 dwar

-0.70

æ©Ł

-0.69

 differe

-0.67

 Dwar

-0.66

oslov

-0.64

POSITIVE LOGITS

odcast

1.14

redict

1.11

ivot

1.10

ossession

1.10

ilot

1.09

ossible

1.07

ulse

1.06

etition

1.06

ORTS

1.01

ACE

1.01

Activations Density 0.024%

financial entities or terms, particularly the S&P index

references to the Standard & Poor's (S&P) stock index

No Comments

No Known Activations