INDEX

Explanations

instances where the text describes something as clearly being a certain way or having a particular characteristic

oai_token-act-pair · gpt-3.5-turbo

instances of the word "clearly" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

rella

-0.86

ntil

-0.77

aily

-0.73

eport

-0.73

enaries

-0.72

eries

-0.69

nesota

-0.69

awaru

-0.67

iously

-0.67

ERY

-0.67

POSITIVE LOGITS

 deline

1.11

 differentiated

0.97

 marked

0.95

 distinguish

0.92

 identifiable

0.92

 differentiate

0.84

 communicated

0.84

 articulated

0.83

 stated

0.83

 labelled

0.81

Activations Density 0.044%

instances where the text describes something as clearly being a certain way or having a particular characteristic

instances of the word "clearly" in various contexts

No Comments

No Known Activations