INDEX

Explanations

phrases that signify realization or discovery

oai_token-act-pair · gpt-3.5-turbo

the phrase "that" in various contexts, often indicating knowledge or awareness of a situation

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

orah

-0.68

ãĥ¼ãĤ¯

-0.67

stead

-0.65

aukee

-0.64

idia

-0.63

amia

-0.62

waters

-0.61

mouth

-0.61

gur

-0.58

viks

-0.58

POSITIVE LOGITS

 pesky

0.88

 fateful

0.82

cher

0.81

 they

0.78

izoph

0.74

chery

0.68

chers

0.67

 someday

0.64

chy

0.63

 surrounds

0.62

Activations Density 0.308%

phrases that signify realization or discovery

the phrase "that" in various contexts, often indicating knowledge or awareness of a situation

No Comments

No Known Activations