INDEX

Explanations

consecutive texts containing the word "resort" followed by a verb ending in 'ing'

oai_token-act-pair · gpt-3.5-turbo

instances of the word "resort" 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 @ 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

hemat

-0.70

rod

-0.69

APH

-0.63

arkin

-0.61

warm

-0.61

ector

-0.59

corn

-0.58

older

-0.58

chrom

-0.58

MAT

-0.58

POSITIVE LOGITS

 resorts

0.85

 resort

0.84

geoning

0.79

ulic

0.77

urous

0.74

 Resort

0.72

uations

0.71

itution

0.70

reality

0.69

itous

0.69

Activations Density 0.018%

consecutive texts containing the word "resort" followed by a verb ending in 'ing'

instances of the word "resort" in various contexts

No Comments

No Known Activations