INDEX

Explanations

words related to catharsis

oai_token-act-pair · gpt-3.5-turbo

references to the concept of catharsis

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

culosis

-0.85

 Predators

-0.77

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.75

 Timberwolves

-0.72

nesota

-0.72

 Raptors

-0.72

Http

-0.71

pmwiki

-0.67

 Grizzlies

-0.66

ãĥį

-0.65

POSITIVE LOGITS

ode

1.20

olics

1.08

arine

1.06

olic

1.06

odic

0.97

illon

0.95

odied

0.94

ricular

0.89

alog

0.88

acas

0.85

Activations Density 0.028%

words related to catharsis

references to the concept of catharsis

No Comments

No Known Activations