INDEX

Explanations

adjectives related to degree or level, such as "enough" and "insufficient"

oai_token-act-pair · gpt-3.5-turbo

terms related to authenticity and increasing intensity, particularly in negative contexts

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

anders

-0.75

ploma

-0.73

aden

-0.71

ADS

-0.68

illon

-0.68

astical

-0.67

annis

-0.67

andering

-0.67

antics

-0.65

ategory

-0.64

POSITIVE LOGITS

ly

2.76

LY

1.75

liness

1.35

lys

1.31

lies

1.21

ELY

1.19

fully

1.15

edly

1.14

ity

1.09

liest

1.04

Activations Density 0.124%

adjectives related to degree or level, such as "enough" and "insufficient"

terms related to authenticity and increasing intensity, particularly in negative contexts

No Comments

No Known Activations