INDEX

Explanations

strong negative emotions or ominous events

oai_token-act-pair · gpt-3.5-turbo

expressions of fear or anxiety

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

utra

-0.73

ECD

-0.72

cius

-0.69

elman

-0.68

ONSORED

-0.67

zanne

-0.67

Priv

-0.67

zu

-0.65

Lib

-0.64

ropri

-0.64

POSITIVE LOGITS

locks

1.20

icum

0.93

locked

0.91

 dread

0.89

etheless

0.87

 Dread

0.76

nant

0.74

 cumbers

0.74

wig

0.72

nuts

0.68

Activations Density 0.027%

strong negative emotions or ominous events

expressions of fear or anxiety

No Comments

No Known Activations